© 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. MLP
    9. 2-MLP
    11. 5992
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    combinations and evaluate

    python-code · gemini-2.5-flash-lite

    attribute access on self (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
     model
    -0.07
     low
    -0.06
    if
    -0.06
     elif
    -0.06
     -
    -0.05
     '#
    -0.05
    low
    -0.05
    ;
    -0.05
     ""
    -0.05
    hi
    -0.04
    POSITIVE LOGITS
    alue
    0.12
    udoku
    0.11
     colle
    0.11
    pe
    0.09
    oard
    0.09
    ariable
    0.07
    lose
    0.07
    rontier
    0.07
    aze
    0.07
    arehouse
    0.07
    Activations Density 100.000%

    No Known Activations