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

    Neuronpedia

    INDEX
    Explanations

    color and ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    entery
    0.53
    ըն
    0.50
    戦
    0.49
    押し
    0.48
     jejich
    0.48
    数は
    0.48
     כמה
    0.46
    nama
    0.46
    祭り
    0.46
    คู่
    0.45
    POSITIVE LOGITS
     fender
    0.49
    va
    0.47
    anez
    0.46
     actuators
    0.46
     주문
    0.46
     fenders
    0.46
     двигателя
    0.45
     ingredientes
    0.45
    ಗರ
    0.42
     Цвет
    0.42
    Act Density 0.001%

    No Known Activations