EU AI Act Annex IV compliance audit platform + mechanistic interpretability toolkit. White-box circuit analysis, black-box audit for any model via API. Open source. MIT.
-
Updated
Apr 5, 2026 - Python
EU AI Act Annex IV compliance audit platform + mechanistic interpretability toolkit. White-box circuit analysis, black-box audit for any model via API. Open source. MIT.
Mechanistic interpretability CLI for transformer models on Apple Silicon. Analyze per-layer predictions, monitor activation drift, compare models, discover circuits. MLX-based, no GPU needed.
Practical mechanistic interpretability tools — activation caching, linear probes, activation patching, circuit discovery, and visualization for transformer models
Add a description, image, and links to the circuit-discovery topic page so that developers can more easily learn about it.
To associate your repository with the circuit-discovery topic, visit your repo's landing page and select "manage topics."