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

    Neuronpedia

    INDEX
    Explanations

    Latin suffixes and Greek words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    1.70
    h
    1.68
    ts
    1.54
    t
    1.53
    In
    1.45
    It
    1.43
    time
    1.39
    tions
    1.32
    There
    1.31
    ty
    1.27
    POSITIVE LOGITS
    يد
    1.30
    もの
    1.25
    ۵
    1.25
    ון
    1.23
    フィルタ
    1.21
     પ્રકાર
    1.20
    ные
    1.19
    та
    1.16
    ۰
    1.15
     botched
    1.13
    Act Density 0.629%

    No Known Activations