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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ९
    0.61
    ある
    0.57
    ı
    0.56
    ت
    0.56
    ıları
    0.54
    ხვევ
    0.54
     Deficiency
    0.54
    ва
    0.53
    ್ಟ
    0.53
    ो
    0.53
    POSITIVE LOGITS
    ية
    0.66
    spaper
    0.57
    ﻟ
    0.55
    ist
    0.54
     dnia
    0.53
    まで
    0.52
    扨
    0.52
    ется
    0.51
     dahil
    0.50
    Doch
    0.49
    Act Density 0.398%

    No Known Activations