© 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. 3517
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    z→ip function call (negative activations)

    python-code · gemini-2.5-flash-lite

    csv.DictReader or csv.reader

    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
    [row
    -0.05
    (row
    -0.05
    _for
    -0.04
    thod
    -0.03
     main
    -0.03
    ault
    -0.03
    main
    -0.03
    .f
    -0.03
    -0.03
    ain
    -0.03
    POSITIVE LOGITS
    jk
    0.09
    a
    0.07
    123
    0.05
    am
    0.05
    ad
    0.04
    ol
    0.04
    ger
    0.04
    ai
    0.03
    [c
    0.03
    port
    0.03
    Activations Density 55.588%

    No Known Activations