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

    Neuronpedia

    INDEX
    Explanations

    words starting with pl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     μέσα
    0.42
    a
    0.41
     CGRect
    0.39
    ല്ല
    0.38
     вда
    0.38
    璘
    0.38
    霸
    0.37
    rnd
    0.37
     Kishore
    0.36
    玠
    0.36
    POSITIVE LOGITS
     Pl
    0.82
     प्ल
    0.81
    Pl
    0.77
     пла
    0.73
     ప్
    0.71
     PL
    0.70
     pla
    0.70
     Plut
    0.69
    Пла
    0.67
     プラ
    0.64
    Act Density 0.057%

    No Known Activations