© 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. 1357
    Prev
    Next
    INDEX
    Explanations

    re.findall function (negative activations)

    python-code · gemini-2.5-flash-lite

    The isdigit string 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
    ind
    -0.29
    ile
    -0.24
    urn
    -0.16
    text
    -0.15
    pe
    -0.15
    il
    -0.15
    rom
    -0.14
    ge
    -0.07
    all
    -0.03
     list
    -0.03
    POSITIVE LOGITS
    arest
    0.36
    ari
    0.26
    ary
    0.24
    ¼
    0.20
    code
    0.16
    array
    0.15
    ast
    0.11
    co
    0.10
    ĺ
    0.08
    ant
    0.05
    Activations Density 99.907%

    No Known Activations