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

    Neuronpedia

    INDEX
    Explanations

    sound and audio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ás
    0.61
    ラー
    0.61
    o
    0.61
    曛
    0.58
    oja
    0.57
    ında
    0.55
     মূল্য
    0.55
     lumière
    0.54
    สู่
    0.54
    0.54
    POSITIVE LOGITS
    (
    0.65
    "
    0.65
     be
    0.65
     تب
    0.61
    {
    0.61
     as
    0.60
    ون
    0.60
     الب
    0.58
    ަ
    0.58
    E
    0.57
    Act Density 0.328%

    No Known Activations