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

    Neuronpedia

    INDEX
    Explanations

    lists and alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Что
    0.70
    Примеча
    0.61
     ciudades
    0.58
    Почему
    0.58
     tailles
    0.58
     их
    0.57
    Те
    0.57
     configurações
    0.57
     т
    0.56
     naturaleza
    0.55
    POSITIVE LOGITS
     a
    0.82
    ad
    0.80
    a
    0.75
    u
    0.71
    ↵↵
    0.63
    ),
    0.61
    ;
    0.61
    i
    0.59
    A
    0.59
     to
    0.56
    Act Density 0.019%

    No Known Activations