© 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. 454
    Prev
    Next
    INDEX
    Explanations

    string method `is`

    python-code · gemini-2.5-flash-lite

    list insert method call (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
    50
    -0.22
    500
    -0.21
    ush
    -0.20
    49
    -0.20
    ĵ
    -0.18
    48
    -0.17
    47
    -0.15
    ep
    -0.13
    51
    -0.12
    op
    -0.12
    POSITIVE LOGITS
    verse
    0.07
    33
    0.07
     print
    0.06
    xt
    0.06
     while
    0.05
    3
    0.03
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 99.934%

    No Known Activations