© 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. 1164
    Prev
    Next
    INDEX
    Explanations

    uniform function call (negative activations)

    python-code · gemini-2.5-flash-lite

    comparison operators after attribute access

    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
    500
    -0.26
    200
    -0.25
    300
    -0.24
    150
    -0.18
     I
    -0.18
    120
    -0.17
    100
    -0.17
     name
    -0.15
    _id
    -0.14
    _name
    -0.13
    POSITIVE LOGITS
    .index
    0.14
     !=
    0.11
     on
    0.11
    _len
    0.10
    _co
    0.06
    35
    0.06
    15
    0.04
     +
    0.03
    '
    0.00
    !
    0.00
    Activations Density 100.000%

    No Known Activations