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

    Neuronpedia

    INDEX
    Explanations

    units and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    certified
    0.52
     ด
    0.45
     speedy
    0.44
     وزن
    0.44
     wat
    0.44
     ҳа
    0.43
     वेगवेगळ्या
    0.43
    your
    0.42
     Пре
    0.42
     ಒಂದು
    0.42
    POSITIVE LOGITS
    ateľ
    0.43
    살
    0.42
    過ご
    0.41
     negocios
    0.41
    Year
    0.41
    .
    0.40
    ">
    0.40
    람
    0.40
    Seth
    0.39
    看出
    0.39
    Act Density 0.000%

    No Known Activations