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

    Neuronpedia

    INDEX
    Explanations

    doubt and uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Виктор
    0.66
    ی
    0.65
    ан
    0.62
    0.61
    observations
    0.60
    ЕН
    0.56
    이스
    0.54
     posición
    0.54
     نوٹ
    0.54
    ва
    0.52
    POSITIVE LOGITS
    ;
    1.07
     in
    1.05
    N
    0.90
    Y
    0.83
    F
    0.80
    S
    0.80
    P
    0.78
    AD
    0.77
    B
    0.72
     at
    0.72
    Act Density 0.001%

    No Known Activations