Lightweight exploratory toolkit inspired by Goodfire-style neural-geometry experiments — find circular representations, Fourier features, and modular-arithmetic geometry in LLM activations. Not affiliated with Goodfire.
pytorch transformer modular-arithmetic representation-learning fourier-analysis interpretability probing huggingface activation-analysis large-language-models llm mechanistic-interpretability neural-geometry goodfire circular-representations
-
Updated
May 17, 2026 - Python