© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

CIRCUITGPT-PYTHON · 6-MLP · 2387 ｜ Neuronpedia

Home
OpenAI · Weight-Sparse Transformers
CircuitGPT-Python
MLP
6-MLP
2387

INDEX

Circuit Sparsity

No connected neurons data available

Explanations

`sorted()` with `key`

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

ters

-0.09

ter

-0.09

ault

-0.07

_rate

-0.06

-0.06

-0.05

 search

-0.05

ror

-0.05

 default

-0.05

_search

-0.04

POSITIVE LOGITS

 start

0.08

_start

0.06

0.06

0.05

_left

0.05

 left

0.05

 source

0.05

start

0.05

.start

0.05

irst

0.05

Activations Density 1.286%

No Known Activations