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

    Neuronpedia

    INDEX
    Explanations

    state or category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    F
    1.10
    B
    1.02
    g
    1.01
    G
    1.00
     l
    0.97
    E
    0.95
    D
    0.93
    C
    0.92
    L
    0.91
    ل
    0.89
    POSITIVE LOGITS
    ्स
    0.72
     aspekt
    0.72
    рья
    0.72
     zumindest
    0.70
    '،
    0.69
     empfohlen
    0.69
     раствор
    0.67
     Möglichkeiten
    0.67
     oder
    0.65
     окружающей
    0.65
    Act Density 0.239%

    No Known Activations