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

    Neuronpedia

    INDEX
    Explanations

    one of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     někter
    0.49
    some
    0.47
     niektó
    0.40
     alguno
    0.40
     bunlar
    0.39
     منها
    0.38
     Algun
    0.38
     Parmi
    0.38
    SOME
    0.37
     niektor
    0.37
    POSITIVE LOGITS
     few
    0.56
     немно
    0.50
     poucos
    0.46
     pocas
    0.46
     Few
    0.46
     coisas
    0.43
     sedikit
    0.43
     handful
    0.43
     poche
    0.42
     અને
    0.42
    Act Density 0.003%

    No Known Activations