© 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. 7243
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `__(` or `def` or `import`

    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
    -
    -0.07
    etween
    -0.06
    ĭ
    -0.05
    lan
    -0.05
    ater
    -0.04
     -
    -0.04
    oth
    -0.04
    ffe
    -0.04
    ip
    -0.03
    duct
    -0.03
    POSITIVE LOGITS
     zip
    0.07
    ze
    0.06
    Z
    0.06
     break
    0.05
     q
    0.05
    iz
    0.05
    X
    0.04
    q
    0.04
    ize
    0.04
    z
    0.04
    Activations Density 50.856%

    No Known Activations