© 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. 2-MLP
    11. 3520
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    range o index

    python-code · gemini-2.5-flash-lite

    function call and definition parameters (negative activations)

    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
     on
    -0.05
    on
    -0.05
     contin
    -0.04
    zero
    -0.03
    one
    -0.03
    (he
    -0.02
     P
    -0.02
    9
    -0.02
    59
    -0.02
    P
    -0.01
    POSITIVE LOGITS
    .heapp
    0.07
    alue
    0.07
    ariable
    0.06
    ariables
    0.06
    Ô
    0.06
    Æ
    0.06
    udok
    0.06
    igh
    0.06
    mmon
    0.05
    isited
    0.05
    Activations Density 100.000%

    No Known Activations