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

    Neuronpedia

    INDEX
    Explanations

    influencing fashion and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     заку
    0.57
    ка
    0.54
    ಿಯಾ
    0.49
     засо
    0.47
     неба
    0.47
    轻轻
    0.46
    cinas
    0.45
    нили
    0.44
    苼
    0.44
    AntiForgery
    0.44
    POSITIVE LOGITS
     or
    0.66
     injury
    0.53
     be
    0.50
     not
    0.50
     enero
    0.48
    Plus
    0.48
     injure
    0.47
     hoje
    0.47
     advantage
    0.46
     errori
    0.46
    Act Density 0.000%

    No Known Activations