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

    Neuronpedia

    INDEX
    Explanations

    quantum state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.50
     not
    0.49
    ours
    0.49
    ול
    0.47
    chlorate
    0.46
    抬头
    0.46
     plot
    0.45
     pumping
    0.45
     sinus
    0.45
     mưa
    0.45
    POSITIVE LOGITS
     ആയിരുന്നു
    0.59
     کولو
    0.57
     ချ
    0.57
     Entscheid
    0.55
     جناح
    0.55
     മിക
    0.55
    ে
    0.55
     الكم
    0.54
     болезнь
    0.54
    DataXYZ
    0.54
    Act Density 0.023%

    No Known Activations