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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.46
    it
    0.42
    you
    0.41
    y
    0.41
     مثل
    0.41
    מ
    0.41
     ر
    0.40
    m
    0.40
     you
    0.40
     id
    0.38
    POSITIVE LOGITS
     séptimo
    0.42
     теркәлү
    0.41
     vía
    0.40
     soirée
    0.40
    Ⴀ
    0.39
    ႃႇ
    0.39
     serviceable
    0.39
    人材
    0.39
     renovación
    0.39
     नवम्बर
    0.38
    Act Density 0.120%

    No Known Activations