© 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. 908
    Prev
    Next
    INDEX
    Explanations

    list slicing and multiplication (negative activations)

    python-code · gemini-2.5-flash-lite

    string literal argument to execute

    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
    (num
    -0.28
    num
    -0.19
    .num
    -0.19
     num
    -0.19
     number
    -0.13
    _num
    -0.13
    (n
    -0.07
    act
    -0.06
    (i
    -0.06
    op
    -0.06
    POSITIVE LOGITS
     that
    0.16
     command
    0.09
    il
    0.08
     ex
    0.06
    result
    0.05
     min
    0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 95.049%

    No Known Activations