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

    Neuronpedia

    INDEX
    Explanations

    exotic/alluvial/gall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dır
    0.29
     ۸
    0.27
    𝓼
    0.27
    ۹
    0.27
    و
    0.26
    苃
    0.26
    8
    0.26
    ด์
    0.26
    دين
    0.26
    די
    0.25
    POSITIVE LOGITS
    ad
    0.41
    .
    0.39
     to
    0.38
    >
    0.37
    '
    0.37
    -
    0.35
    n
    0.33
    z
    0.33
    ó
    0.33
    ä
    0.32
    Act Density 0.000%

    No Known Activations