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

    Neuronpedia

    INDEX
    Explanations

    ... punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     satisfacción
    0.73
    ଡ
    0.73
     лежа
    0.71
    ֣
    0.69
     traces
    0.68
     האל
    0.67
    ду
    0.66
    像
    0.66
    traces
    0.65
     разобра
    0.65
    POSITIVE LOGITS
    !
    1.81
    ;
    1.64
    .),
    1.59
    !.
    1.58
    .;
    1.57
     เพราะ
    1.56
    !,
    1.55
    !),
    1.53
    !;
    1.50
    .
    1.48
    Act Density 0.118%

    No Known Activations