© 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. 867
    Prev
    Next
    INDEX
    Explanations

    .isalpha(), .isnumeric() (negative activations)

    python-code · gemini-2.5-flash-lite

    starts `dictionary` definition or `difference`

    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
    .de
    -0.12
     last
    -0.09
     O
    -0.06
    _a
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    POSITIVE LOGITS
     Create
    0.30
    itial
    0.27
    stance
    0.22
     Initialize
    0.21
     defaultdict
    0.19
    .graph
    0.18
     [[
    0.16
    network
    0.16
    _graph
    0.15
     Graph
    0.14
    Activations Density 100.000%

    No Known Activations