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

    Neuronpedia

    INDEX
    Explanations

    predicting arrival and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thief
    0.41
     верхней
    0.41
     ویکی‌پ
    0.38
     centrale
    0.38
     anomalous
    0.38
     вере
    0.38
    セット
    0.37
     méthodique
    0.37
     நூ
    0.37
     პირ
    0.36
    POSITIVE LOGITS
    Beta
    0.40
    OLIS
    0.39
    vina
    0.39
    فاع
    0.38
    اتو
    0.38
    Accounts
    0.37
    ౌ
    0.37
    ίκη
    0.37
    ాత
    0.36
    喹
    0.36
    Act Density 0.000%

    No Known Activations