© 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. 823
    Prev
    Next
    INDEX
    Explanations

    `[']`, `.` or `(` after variable (negative activations)

    python-code · gemini-2.5-flash-lite

    elif condition or indexing

    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
    attern
    -0.18
     pattern
    -0.17
    house
    -0.17
    ype
    -0.17
     base
    -0.16
    line
    -0.16
    ode
    -0.16
    _path
    -0.16
    Į
    -0.15
    path
    -0.15
    POSITIVE LOGITS
    ¦
    0.19
    are
    0.18
     that
    0.17
    xt
    0.15
    label
    0.15
     label
    0.15
    time
    0.14
     oper
    0.14
     Node
    0.13
    ars
    0.12
    Activations Density 92.508%

    No Known Activations