© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5773
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    key in a lambda function

    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
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    place
    -0.04
     pro
    -0.02
     e
    -0.02
     {
    -0.01
     length
    -0.01
    ].
    -0.01
    ab
    -0.01
    _str
    -0.01
    _li
    -0.01
    '
    0.00
    POSITIVE LOGITS
     print
    0.05
    ))
    0.04
     pass
    0.04
    0.03
    0.03
    0.03
    ())↵
    0.03
    0.03
    0.03
     while
    0.03
    Activations Density 28.270%

    No Known Activations