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

    Neuronpedia

    INDEX
    Explanations

    don't / won't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    便是
    0.63
    である
    0.62
    滓
    0.59
    bilir
    0.58
    としての
    0.57
     vei
    0.56
    における
    0.55
    べく
    0.55
     आयी
    0.55
     Forth
    0.55
    POSITIVE LOGITS
    '
    1.04
    ’
    0.98
    keys
    0.92
    comstockfootage
    0.92
    檛
    0.83
    稚
    0.81
    othing
    0.80
    KEYS
    0.79
    ât
    0.77
    ít
    0.76
    Act Density 0.415%

    No Known Activations