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

    Neuronpedia

    INDEX
    Explanations

    Insurance/damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نص
    -0.07
     дер
    -0.07
     NSDate
    -0.07
     tst
    -0.06
    合格
    -0.06
     pořád
    -0.06
    (Target
    -0.06
     kys
    -0.06
     valido
    -0.06
     attrs
    -0.06
    POSITIVE LOGITS
     opinion
    0.07
     ALERT
    0.06
     ऑनल
    0.06
    +'"
    0.06
    жд
    0.06
    .getHours
    0.06
    iyordu
    0.06
    ického
    0.06
     posting
    0.06
     congratulate
    0.06
    Act Density 0.015%

    No Known Activations