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

    Neuronpedia

    INDEX
    Explanations

    years and dates

    np_acts-logits-general · gemini-2.5-flash-lite

    Dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.67
     (
    0.62
    k
    0.59
     you
    0.58
     is
    0.55
     A
    0.52
    คุณ
    0.52
     This
    0.51
     On
    0.50
     "
    0.50
    POSITIVE LOGITS
    را
    0.66
    {
    0.65
    ли
    0.61
    be
    0.61
     in
    0.59
    もら
    0.59
    ല
    0.58
    在
    0.58
    ور
    0.57
    پ
    0.57
    Act Density 0.384%

    No Known Activations