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

    Neuronpedia

    INDEX
    Explanations

    concepts and principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ای
    0.50
    ‌های
    0.50
    ‌ی
    0.41
    过
    0.40
    type
    0.40
    ‌ای
    0.40
     “
    0.39
    chus
    0.39
    tight
    0.39
    Основ
    0.38
    POSITIVE LOGITS
     neler
    0.52
     ktoré
    0.51
     jotka
    0.50
     amelyek
    0.49
     laterales
    0.49
    এছ
    0.47
     técnicas
    0.46
    ᱹ
    0.46
     principales
    0.45
    lerimiz
    0.45
    Act Density 1.350%

    No Known Activations