neuronpedia AGENTS.md

neuronpedia AGENTS.md is an instructions file for Codex, OpenCode from hijohnnylin/neuronpedia. It costs 7,202 tokens per session, scanned A, original, Apache-2.0.

Development instructions for Neuronpedia, a website and research platform for examining and experimenting with features inside neural networks.

In plain words
What is it for?
Use them when working on model inference, neuron or feature explanations, circuit graphs, sparsity tools, the web app, or the SDK.
Why use it?
They describe the repository layout, its Python services, web application, generated files, and configuration rules so changes go in the right place.

Instructions file for CodexOpenCode

About the project

Neuronpedia is an open-source platform for examining how neural networks work through model activations, circuits, feature representations, and related analyses. Researchers and developers use it to inspect, search, score, visualize, and export interpretability data. Its catalogue add-ons support local development and workflows around the platform.

hijohnnylin/neuronpedia · 1,122 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/hijohnnylin/neuronpedia/agents-md
Clone the repo
git clone --depth 1 https://github.com/hijohnnylin/neuronpedia

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for neuronpedia AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hijohnnylin/neuronpedia/agents-md.svg)](https://agentmods.dev/instructions/hijohnnylin/neuronpedia/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hijohnnylin/neuronpedia/agents-md"><img src="https://agentmods.dev/badge/instructions/hijohnnylin/neuronpedia/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,202 This file is loaded in full into every session.
When invoked 7,202 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.07202 $0.07202
Opus 5 $0.03601 $0.03601
Sonnet 5 $0.01440 $0.01440
Haiku 4.5 $0.00720 $0.00720

Measured 4d ago against content hash 5c4a70ee65c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

neuronpedia AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Neuronpedia Development Guide

This file is the single source of truth for agent instructions, and every harness reads it — see "Agent instruction files" at the bottom before adding rules anywhere else.

Repository layout

apps/
  autointerp/
  graph/
  inference/
  nla/
  sparsity/
  webapp/
    lib/api/        # generated: <app>.d.ts from each server's openapi.json
docs/               # the long-form reasoning this file's rules point at
utils/
webapp-python-client/   # hand-written public SDK

Neuronpedia is an interpretability website/platform: a reference for what is inside a neural network, plus tools for researchers to experiment with those internals — viewing activations for a given 'neuron' (or feature/latent), steering on them, tracing circuits.

apps/ holds most of the code. Five of the six are Python FastAPI servers, called by the webapp rather than by users directly:

  • inference has the actual model loaded, and serves anything requiring a forward pass. The webapp calls it mostly from apps/webapp/lib/utils/inference.ts.
  • autointerp explains and scores neurons/features/latents. Called mostly from apps/webapp/lib/utils/autointerp.ts.
  • graph, nla and sparsity are the attribution-graph, Natural Language Autoencoder (activation vector <-> text) and sparse-circuit services.

webapp is the sixth: a Next.js app that is both the frontend and the user-facing API under apps/webapp/app/api. Its database schema is apps/webapp/prisma/schema.prisma, and it has its own AGENTS.md with frontend conventions.

Cross-server types are generated from the Python, in one direction. Each server's pydantic models are the source of truth; make openapi regenerates every spec and every lib/api/<app>.d.ts from them. There is no hand-written spec and no client package in the loop, so adding an endpoint means writing pydantic models, not editing a schema file. The full workflow, and which servers are camelCase on the wire versus deliberately snake_case, is under "Cross-server APIs" below.

Read the full file on GitHub · 466 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 466 lines · 7,202 tokens per session scan A 5c4a70ee65c5

Subscribe to this mod's changes

neuronpedia AGENTS.md is an instructions file published in the GitHub repository hijohnnylin/neuronpedia (1,122 stars, last pushed yesterday), licensed Apache-2.0. It adds 7,202 tokens to every session, about $0.0360 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories