© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 6653
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    button keyword

    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
    en
    -0.07
    tim
    -0.04
    sp
    -0.04
    er
    -0.03
    g
    -0.02
    st
    -0.02
     e
    -0.02
    '
    0.00
    #
    0.00
    &
    0.00
    POSITIVE LOGITS
    as
    0.18
    a
    0.14
    ¹
    0.11
    thod
    0.08
    are
    0.08
    verage
    0.08
    ash
    0.07
    da
    0.06
    quest
    0.05
    ab
    0.04
    Activations Density 4.787%

    No Known Activations