© 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. 1257
    Prev
    Next
    INDEX
    Explanations

    string literals and numbers (negative activations)

    python-code · gemini-2.5-flash-lite

    chr() with ascii offset

    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
    loat
    -0.29
     float
    -0.26
     math
    -0.22
     obstac
    -0.19
     calculate
    -0.19
    oly
    -0.17
     /
    -0.17
    _r
    -0.16
    18
    -0.13
    _an
    -0.11
    POSITIVE LOGITS
    rules
    0.12
     all
    0.06
     return
    0.05
     +
    0.05
     result
    0.05
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Activations Density 100.000%

    No Known Activations