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

    Neuronpedia

    INDEX
    Explanations

    f" string literals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ){
    0.90
    ровать
    0.71
     миро
    0.69
     acha
    0.66
     diminish
    0.65
     спосо
    0.64
    rennt
    0.64
     возникновения
    0.64
     situazione
    0.63
    acchati
    0.63
    POSITIVE LOGITS
    $\
    0.79
    ASON
    0.66
    단을
    0.64
    치
    0.64
    ’
    0.63
    ३
    0.61
    사를
    0.61
     tedes
    0.58
    IONS
    0.58
    ων
    0.57
    Act Density 0.009%

    No Known Activations