© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

CIRCUITGPT-PYTHON · 6-MLP · 4979 ｜ Neuronpedia

Home
OpenAI · Weight-Sparse Transformers
CircuitGPT-Python
MLP
6-MLP
4979

INDEX

Circuit Sparsity

No connected neurons data available

Explanations

assignment statement

python-code · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

16,384 prompts, 256 tokens each

Dataset (Dashboard)

neuronpedia/python-code-simplified

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.05

gh

-0.05

mit

-0.04

ss

-0.04

.is

-0.04

 heapq

-0.04

art

-0.04

 Returns

-0.03

 Return

-0.03

ses

-0.03

POSITIVE LOGITS

½

0.07

ents

0.05

0.05

ent

0.05

if

0.05

nt

0.04

ency

0.04

hild

0.04

hildren

0.04

lust

0.04

Activations Density 76.360%

No Known Activations