© 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. 1028
    Prev
    Next
    INDEX
    Explanations

    `hexdigest()` or `upper()` (negative activations)

    python-code · gemini-2.5-flash-lite

    re.findall method

    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
     found
    -0.10
     pro
    -0.04
     an
    -0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    !
    0.00
    POSITIVE LOGITS
     all
    0.28
    all
    0.27
     any
    0.17
    ly
    0.12
     each
    0.11
    ree
    0.08
     possible
    0.07
     that
    0.06
    ay
    0.06
     from
    0.05
    Activations Density 99.999%

    No Known Activations