© 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. 740
    Prev
    Next
    INDEX
    Explanations

    assignment to list literal (negative activations)

    python-code · gemini-2.5-flash-lite

    variable name `g` in list initialization

    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
    bers
    -0.08
     assign
    -0.07
     app
    -0.07
    ine
    -0.07
     |
    -0.06
    .con
    -0.05
     log
    -0.04
    .name
    -0.04
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
    idth
    0.27
    _len
    0.25
    len
    0.25
     size
    0.24
     len
    0.23
    size
    0.23
    _length
    0.21
     length
    0.21
    _size
    0.20
    .num
    0.18
    Activations Density 100.000%

    No Known Activations