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

    Neuronpedia

    INDEX
    Explanations

    books and articles on topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ิ
    0.48
     sentences
    0.45
    语句
    0.44
    ι
    0.43
     నో
    0.43
    ıcı
    0.42
    编码
    0.42
    Expr
    0.41
    学员
    0.41
    ícul
    0.39
    POSITIVE LOGITS
     tema
    0.54
     intensively
    0.50
     thème
    0.44
     Thema
    0.43
     Marken
    0.41
    روض
    0.40
     patriotism
    0.40
    بحث
    0.40
     الموضوع
    0.40
     Tema
    0.40
    Act Density 0.002%

    No Known Activations