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

    Neuronpedia

    INDEX
    Explanations

    has to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻨ
    0.68
    ﺩ
    0.66
     később
    0.65
     později
    0.63
    o
    0.60
    ad
    0.59
    ﺱ
    0.59
    sin
    0.58
    the
    0.57
    ography
    0.57
    POSITIVE LOGITS
     can
    0.91
    ח
    0.89
    ع
    0.81
    ’
    0.79
    ال
    0.78
    א
    0.78
     is
    0.77
    માં
    0.77
    ح
    0.77
    ，
    0.76
    Act Density 0.020%

    No Known Activations