Instructions file
Instructions for ndif-team/nnsight, covering nnsight — agent guide, how to use this file, by task, "i want multi-token / autoregressive generation" and "i want to run multiple prompts at once".
Instructions file
Instructions for ndif-team/ndif, covering claude.md — ndif agent guide, what ndif is, top-level layout, architecture at a glance and security sandbox (the highest-stakes area).
Plugin Claude Code
Plugin marketplace listing 1 plugin: nnsight.
Instructions file
Instructions for ndif-team/skills, covering claude.md, project overview, architecture, adding a new skill and nnsight patterns used across skills.
Plugin Claude Code
Neural network interpretability with nnsight - tracing, patching, steering, and analysis.
Skill Claude CodeCodex
Causal intervention via activation patching to identify important model components. Use when determining which layers, heads, or positions are causally responsible for model behavior.
Skill Claude CodeCodex
Gradient-based approximation to activation patching for scalable circuit analysis. Use when activation patching is too slow or when analyzing many components simultaneously.
Skill Claude CodeCodex
Causal mediation analysis to identify which model components mediate specific behaviors. Use when investigating how information flows through the network and which neurons or layers are causally responsible for outputs.
Skill Claude CodeCodex
Decode intermediate layer predictions using the Logit Lens technique. Use when analyzing what a model predicts at each layer, understanding information flow, or visualizing layer-wise processing.
Skill Claude CodeCodex
Control model behavior through persistent edits and steering interventions. Use when modifying model outputs, applying steering vectors, or creating persistently modified model versions.
Skill Claude CodeCodex
Core nnsight concepts for neural network interpretability. Use when setting up models, tracing activations, saving values, or making basic interventions on model internals.
Skill Claude CodeCodex
Optimize nnsight code for remote execution on NDIF. Use whenever the user is writing, reviewing, or refactoring nnsight code that runs against NDIF (any usage of remote=True, model.session, or models too large to run locally like Llama-70B/405B), even if they don't ask for "optimization" explicitly — naive remote code…