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

    Neuronpedia

    INDEX
    Explanations

    muted tones and colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是一種
    1.36
     ہے
    1.30
    是一個
    1.30
    يا
    1.29
    Я
    1.29
     Только
    1.26
    是一种
    1.23
    У
    1.23
    Υ
    1.23
     Использу
    1.22
    POSITIVE LOGITS
     the
    1.69
     a
    1.67
     in
    1.49
     from
    1.41
     on
    1.41
     by
    1.26
     with
    1.22
     as
    1.12
     at
    1.12
    不久
    1.11
    Act Density 0.041%

    No Known Activations