Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    main

    np_max-act · gemini-2.0-flash

    This neuron detects the Python idiom that checks for “if __name__ == '__main__'” to mark the script’s entry point.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (window
    -0.06
    .getB
    -0.06
    uggage
    -0.06
     illustrations
    -0.06
     अख
    -0.06
     Ot
    -0.06
    Wis
    -0.06
    (options
    -0.06
    Again
    -0.06
    ::/
    -0.06
    POSITIVE LOGITS
     Bordeaux
    0.07
    主要
    0.07
    93
    0.07
    sdale
    0.07
    XY
    0.07
     Suggestions
    0.07
    assessment
    0.06
     ‐
    0.06
     audible
    0.06
     "\">
    0.06
    Act Density 0.000%

    No Known Activations