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

    Neuronpedia

    INDEX
    Explanations

    zoom, Cream, GAMING

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.53
    不喜欢
    0.52
    inase
    0.49
    явля
    0.48
    ಕರಣ
    0.48
    innt
    0.47
    看的
    0.46
    滤波器
    0.46
    وين
    0.46
    眄
    0.46
    POSITIVE LOGITS
    ية
    0.57
    :
    0.52
     كه
    0.49
     powied
    0.47
    centaje
    0.47
    (
    0.46
     řek
    0.45
    <0x80>
    0.44
    하다
    0.43
     по
    0.43
    Act Density 0.277%

    No Known Activations