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

    Neuronpedia

    INDEX
    Explanations

    either or something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ハート
    0.43
     যাতে
    0.42
    会不会
    0.41
     よろしく
    0.40
     wouldnt
    0.39
     simbol
    0.39
     whatnot
    0.39
     noved
    0.38
    ূর্তি
    0.38
    都會
    0.38
    POSITIVE LOGITS
     either
    0.91
     entweder
    0.84
    something
    0.83
    Something
    0.80
    Either
    0.80
     Either
    0.80
    要么
    0.79
    either
    0.79
     либо
    0.78
     something
    0.78
    Act Density 0.010%

    No Known Activations