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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash

    The neuron detects lowercase letter list markers (e.g. “a)”, “b)”, “c)”, etc.) in enumerated lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    2
    -0.08
    5
    -0.07
    3
    -0.07
    具
    -0.06
    archivo
    -0.06
    iliation
    -0.06
    1
    -0.06
    11
    -0.06
    956
    -0.06
    (/*
    -0.06
    POSITIVE LOGITS
     бет
    0.07
     gou
    0.07
    пон
    0.06
     associate
    0.06
     can
    0.06
    emez
    0.06
    [vertex
    0.06
    dez
    0.06
    город
    0.06
    meric
    0.06
    Act Density 0.021%

    No Known Activations