© 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. Residual Stream
    9. 7-RESID
    11. 470
    Prev
    Next
    INDEX
    Explanations

    string literals

    python-code · gemini-2.5-flash-lite

    list constructor or initializer (negative activations)

    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
    ache
    -0.21
     dep
    -0.11
     ex
    -0.09
     visited
    -0.06
     s
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    POSITIVE LOGITS
    ray
    0.21
    que
    0.12
    _sum
    0.12
    .set
    0.12
    (list
    0.11
    str
    0.09
    array
    0.09
    _str
    0.07
    _set
    0.07
    ctor
    0.06
    Activations Density 100.000%

    No Known Activations