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

    Neuronpedia

    INDEX
    Explanations

    how are you today?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    리는
    0.87
    राबरी
    0.84
     desenvolv
    0.82
     නමුත්
    0.80
    ढ़ाई
    0.78
    ﻜ
    0.78
    ્ર
    0.77
    ான்
    0.77
    룹
    0.77
    ۳
    0.77
    POSITIVE LOGITS
    i
    1.47
    g
    1.43
    the
    1.39
    j
    1.29
    ي
    1.28
    y
    1.26
    t
    1.21
    z
    1.15
    ت
    1.14
     (
    1.11
    Act Density 0.010%

    No Known Activations