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

    Neuronpedia

    INDEX
    Explanations

    explaining with "let's"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    me
    0.82
     me
    0.73
    ’
    0.62
    ’:
    0.61
    ’.
    0.61
    ']/
    0.61
    '].
    0.56
    ’,
    0.56
     mo
    0.56
    ']=
    0.55
    POSITIVE LOGITS
     citado
    0.81
     vamos
    0.77
     нас
    0.77
     conocemos
    0.76
    Arts
    0.75
     озна
    0.75
    LET
    0.74
     આપણા
    0.73
     погру
    0.73
    АСС
    0.72
    Act Density 0.360%

    No Known Activations