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

    Neuronpedia

    INDEX
    Explanations

    engine cylinder components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    1.21
    as
    0.90
    c
    0.89
    lers
    0.87
    giving
    0.87
    ي
    0.86
    dı
    0.84
    oje
    0.84
    n
    0.84
    nings
    0.82
    POSITIVE LOGITS
    '
    1.03
    <0x0D>
    0.90
    </b>
    0.88
    0
    0.88
    рт
    0.87
    кат
    0.86
    는
    0.85
    О
    0.85
    Is
    0.82
    の色
    0.81
    Act Density 0.001%

    No Known Activations