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

    Neuronpedia

    INDEX
    Explanations

    wake up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.79
    al
    0.79
    ir
    0.79
    u
    0.79
    ar
    0.78
    t
    0.77
    é
    0.76
    ang
    0.73
    ol
    0.71
    y
    0.71
    POSITIVE LOGITS
    จาก
    0.66
     awakens
    0.63
    醒
    0.61
     awake
    0.60
    覚
    0.58
     জেগে
    0.57
    起来
    0.56
    FromNib
    0.55
    )’
    0.55
     ಇದರಿಂದ
    0.54
    Act Density 0.052%

    No Known Activations