© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1601
    Prev
    Next
    INDEX
    Explanations

    string manipulation methods (negative activations)

    python-code · gemini-2.5-flash-lite

    re.sub method call

    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
    »
    -0.33
    _li
    -0.26
    li
    -0.20
    ud
    -0.18
     l
    -0.18
     Return
    -0.15
     Tuple
    -0.13
     pi
    -0.08
    lay
    -0.05
     c
    -0.01
    POSITIVE LOGITS
     lon
    0.29
    Ħ
    0.15
    lat
    0.11
    loc
    0.08
     lat
    0.08
    _l
    0.04
    as
    0.04
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 100.000%

    No Known Activations