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

    Neuronpedia

    INDEX
    Explanations

    contains a dielectric gel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windigkeit
    0.47
    ennzeichnet
    0.45
    理解
    0.44
    requenz
    0.44
    문을
    0.43
     Г
    0.42
    장을
    0.41
    ök
    0.41
    ln
    0.41
     unsere
    0.41
    POSITIVE LOGITS
    เข้า
    0.57
     stabilizes
    0.47
     ダイヤ
    0.44
     salida
    0.43
     reseller
    0.42
     perform
    0.42
     StatusBar
    0.42
     pullback
    0.41
     salido
    0.41
     basura
    0.41
    Act Density 0.000%

    No Known Activations