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

    Neuronpedia

    INDEX
    Explanations

    properties and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.51
     is
    0.43
     on
    0.43
     beerCount
    0.41
     ERP
    0.41
     parametr
    0.39
     a
    0.38
     have
    0.38
     exorc
    0.38
     to
    0.38
    POSITIVE LOGITS
    ли
    0.45
    ierung
    0.42
     tertentu
    0.42
    ઠળ
    0.42
    IM
    0.41
     tomado
    0.41
    en
    0.41
     kter
    0.40
    вной
    0.40
    EN
    0.40
    Act Density 0.476%

    No Known Activations