© 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. 7604
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    clear() method

    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
    _to
    -0.05
    he
    -0.05
    _from
    -0.04
     to
    -0.04
     from
    -0.04
    rom
    -0.03
    tive
    -0.03
    hi
    -0.03
    from
    -0.03
     ->
    -0.02
    POSITIVE LOGITS
    s
    0.10
    ses
    0.08
    dex
    0.08
    se
    0.07
    sed
    0.06
    ser
    0.06
    sible
    0.06
    si
    0.05
    ¹
    0.05
    ud
    0.05
    Activations Density 80.732%

    No Known Activations