© 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. Residual Stream
    9. 7-RESID
    11. 962
    Prev
    Next
    INDEX
    Explanations

    parse arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    list element access

    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
    ange
    -0.35
    ust
    -0.25
    ct
    -0.18
    lit
    -0.16
    ce
    -0.15
    ho
    -0.14
    cept
    -0.14
    mp
    -0.13
    vi
    -0.13
    ate
    -0.12
    POSITIVE LOGITS
    ake
    0.14
    mo
    0.09
    ac
    0.05
    ob
    0.04
    e
    0.03
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Activations Density 100.000%

    No Known Activations