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

    Neuronpedia

    INDEX
    Explanations

    explaining timelines, terms, or variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.42
    S
    0.41
    Mac
    0.40
    T
    0.40
    인
    0.40
    Pascal
    0.40
    2
    0.38
    乘
    0.38
    B
    0.38
    in
    0.38
    POSITIVE LOGITS
     Без
    0.52
     Вер
    0.50
    problem
    0.49
     Δεν
    0.49
     Вам
    0.48
     Кол
    0.48
     pla
    0.48
     gals
    0.48
     Κα
    0.48
     Αυ
    0.48
    Act Density 0.011%

    No Known Activations