© 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. 310
    Prev
    Next
    INDEX
    Explanations

    part of method names or operands

    python-code · gemini-2.5-flash-lite

    accessing attribute or method after variable (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
    oard
    -0.25
    aze
    -0.24
    blem
    -0.24
    grid
    -0.23
    _grid
    -0.22
     grid
    -0.22
     graph
    -0.22
    udoku
    -0.22
     maze
    -0.22
    .grid
    -0.21
    POSITIVE LOGITS
    turn
    0.08
    ber
    0.07
     iter
    0.07
    unt
    0.07
    ak
    0.06
    ater
    0.05
    _step
    0.05
     moves
    0.04
     steps
    0.04
     qu
    0.04
    Activations Density 100.000%

    No Known Activations