© 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. 3303
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    class, def, import, or @ followed by identifier

    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
    atus
    -0.05
     it
    -0.05
    tail
    -0.05
    ata
    -0.05
    fo
    -0.04
    hor
    -0.04
    oth
    -0.04
    inf
    -0.03
    ations
    -0.03
    os
    -0.03
    POSITIVE LOGITS
    ve
    0.09
    ven
    0.08
    v
    0.07
    der
    0.07
     me
    0.06
    _ve
    0.06
    p
    0.06
    ŀ
    0.06
     ve
    0.06
    vel
    0.06
    Activations Density 18.584%

    No Known Activations