© 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. 79
    Prev
    Next
    INDEX
    Explanations

    string method calls

    python-code · gemini-2.5-flash-lite

    definition of special methods (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
    @
    -0.15
     app
    -0.13
     si
    -0.12
     sy
    -0.12
    of
    -0.11
     gen
    -0.10
    we
    -0.09
     process
    -0.09
     z
    -0.09
     inter
    -0.08
    POSITIVE LOGITS
    [-
    0.22
     ValueError
    0.21
    mbol
    0.20
    "{
    0.20
     enumerate
    0.19
    fset
    0.19
    _counts
    0.18
     self
    0.18
    [
    0.17
    ['
    0.17
    Activations Density 100.000%

    No Known Activations