© 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. 1551
    Prev
    Next
    INDEX
    Explanations

    list element indexing (negative activations)

    python-code · gemini-2.5-flash-lite

    dictionary key access then append

    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
    ({
    -0.18
     {↵
    -0.18
    ['
    -0.16
     '#
    -0.14
    .get
    -0.12
    ["
    -0.12
     If
    -0.12
    ]]
    -0.09
    ])
    -0.08
     O
    -0.08
    POSITIVE LOGITS
     [(
    0.16
     [
    0.16
    /
    0.15
     sorted
    0.12
     np
    0.10
    ([
    0.07
    append
    0.07
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 95.684%

    No Known Activations