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

    Neuronpedia

    INDEX
    Explanations

    at least one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंबई
    0.64
    则是
    0.63
     уважаемые
    0.58
     क्रमशः
    0.57
    ekom
    0.57
    ützen
    0.57
     ulteriori
    0.56
     등에
    0.56
    幅広い
    0.55
     অবশ্য
    0.55
    POSITIVE LOGITS
     one
    3.48
     One
    3.09
    One
    3.02
     ONE
    2.96
    one
    2.95
     satu
    2.89
     één
    2.85
     одного
    2.41
     один
    2.41
    ONE
    2.37
    Act Density 1.452%

    No Known Activations