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

    Neuronpedia

    INDEX
    Explanations

    Пла

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pl
    0.68
     pl
    0.66
    Pl
    0.60
     пла
    0.57
     Pl
    0.57
     PL
    0.55
    PL
    0.53
    Pay
    0.46
    PLS
    0.45
     प्ल
    0.44
    POSITIVE LOGITS
     smear
    0.46
    ओं
    0.41
     smudge
    0.41
    ttä
    0.39
     కళ
    0.39
     स्मिथ
    0.38
     chav
    0.38
    ting
    0.37
     tup
    0.37
     Pasal
    0.37
    Act Density 0.000%

    No Known Activations