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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2414
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    else block terminator (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute assignment 'right'

    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
    {
    -0.02
    ).
    -0.02
     <
    -0.02
    _d
    -0.01
    29
    -0.01
     //
    -0.01
     +
    -0.01
    _di
    -0.01
     *
    -0.01
     Di
    -0.01
    POSITIVE LOGITS
     """
    0.02
     """↵
    0.02
    unction
    0.02
     a
    0.02
    70
    0.02
    .x
    0.02
    _x
    0.02
     an
    0.02
     x
    0.02
    lat
    0.02
    Activations Density 77.391%

    No Known Activations