© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 347
    Prev
    Next
    INDEX
    Explanations

    string literal in re.findall

    python-code · gemini-2.5-flash-lite

    import re (negative activations)

    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
    essage
    -0.25
    dividual
    -0.23
    odel
    -0.18
    arent
    -0.16
    isited
    -0.16
    visited
    -0.15
    ackage
    -0.10
    ă
    -0.08
    _room
    -0.05
    qrt
    -0.04
    POSITIVE LOGITS
     r
    0.14
     #
    0.09
     at
    0.08
     v
    0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    Activations Density 100.000%

    No Known Activations