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

    Neuronpedia

    INDEX
    Explanations

    checks for null or not equal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    1.38
    {
    1.33
    いた
    1.20
    Ο
    1.20
     に
    1.16
     of
    1.16
     a
    1.10
     not
    1.10
     we
    1.09
     =
    1.09
    POSITIVE LOGITS
    '
    1.84
    ]!=
    1.07
    ‘
    1.00
    ang
    0.93
    ح
    0.93
    ším
    0.93
    ig
    0.92
    os
    0.91
    ز
    0.90
    .
    0.90
    Act Density 0.021%

    No Known Activations