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

    Neuronpedia

    INDEX
    Explanations

    qualities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.74
    ل
    0.72
     on
    0.68
     for
    0.67
     as
    0.66
     \
    0.66
    مد
    0.65
    DC
    0.64
    ند
    0.63
     and
    0.61
    POSITIVE LOGITS
    ي
    0.71
     của
    0.70
     solvency
    0.64
     τέ
    0.63
    sufficiency
    0.63
    compatibility
    0.62
    របស់
    0.61
    ຂອງ
    0.60
     tightness
    0.60
    ቱም
    0.58
    Act Density 0.437%

    No Known Activations