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

    Neuronpedia

    INDEX
    Explanations

    closing tags or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     was
    1.13
    >
    1.02
    IN
    1.01
    p
    0.97
    data
    0.96
     you
    0.95
    i
    0.93
    %
    0.89
     It
    0.89
    AD
    0.88
    POSITIVE LOGITS
    ри
    0.95
     Балтбет
    0.93
    ра
    0.89
    ীর
    0.81
    кт
    0.78
     metrizable
    0.77
     অসহায়
    0.76
    지의
    0.76
    ్వ
    0.75
    ј
    0.75
    Act Density 0.001%

    No Known Activations