© 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. 7656
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    calling a method on an instance

    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
    layer
    -0.02
    .append
    -0.01
     not
    -0.01
    ity
    -0.01
     total
    -0.01
    =lambda
    -0.00
    st
    -0.00
     each
    -0.00
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
    _p
    0.07
     p
    0.06
    (p
    0.05
    ĥ
    0.05
    [p
    0.04
    place
    0.04
    pe
    0.04
    port
    0.04
    py
    0.03
     P
    0.03
    Activations Density 21.109%

    No Known Activations