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

    Neuronpedia

    INDEX
    Explanations

    django database migrations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    -2.00
    需要
    -1.52
     
    -1.50
    鲼
    -1.46
    有
    -1.44
    要
    -1.43
    höhung
    -1.41
    case
    -1.41
     certamen
    -1.40
     解説
    -1.38
    POSITIVE LOGITS
     этом
    1.79
     всички
    1.68
    葎
    1.66
     мои
    1.64
     things
    1.61
    masque
    1.60
    colgante
    1.59
    renault
    1.59
    </b>
    1.56
     този
    1.55
    Act Density 0.001%

    No Known Activations