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

    Neuronpedia

    INDEX
    Explanations

    Kim Peek

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.33
    x
    0.31
    c
    0.31
    t
    0.29
    b
    0.29
    0.28
    ги
    0.28
    n
    0.28
    d
    0.27
    -
    0.27
    POSITIVE LOGITS
     Tämä
    0.29
     į
    0.28
     jedoch
    0.26
     زیرمه
    0.26
     poiché
    0.26
    鑣
    0.26
     puisse
    0.25
     është
    0.25
     tačiau
    0.25
     Međutim
    0.25
    Act Density 0.000%

    No Known Activations