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

    Neuronpedia

    INDEX
    Explanations

    catalog, labeled, classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.62
    ن
    1.56
    ע
    1.51
    c
    1.44
    n
    1.35
    ların
    1.34
    ח
    1.31
    ει
    1.30
    রকম
    1.30
    ס
    1.28
    POSITIVE LOGITS
    '
    1.59
    ;
    1.51
    <0x0D>
    1.24
    ,
    1.16
    ’
    1.13
    ↵↵
    1.09
    OF
    1.04
     aplicativo
    1.04
    I
    1.02
    /
    1.00
    Act Density 0.514%

    No Known Activations