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

    Neuronpedia

    INDEX
    Explanations

    multilingual text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ০
    1.19
    i
    1.09
    a
    1.02
    an
    0.95
    ي
    0.92
    as
    0.91
    ം
    0.90
    ed
    0.87
    es
    0.86
    u
    0.83
    POSITIVE LOGITS
    ূট
    0.71
    ajú
    0.71
    По
    0.67
    जनबी
    0.67
    ней
    0.66
    Также
    0.66
    ↵
    0.66
    kiem
    0.65
    اري
    0.65
     Mình
    0.65
    Act Density 0.000%

    No Known Activations