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

    Neuronpedia

    INDEX
    Explanations

    Arabic word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    お
    0.80
     a
    0.75
    </h2>
    0.68
     it
    0.67
     AAU
    0.67
    AA
    0.66
    است
    0.66
    மதி
    0.66
    ↵
    0.65
     Shak
    0.65
    POSITIVE LOGITS
    ي
    1.73
    i
    1.42
    á
    1.30
    é
    1.25
     новом
    1.04
    iunea
    1.02
    י
    0.98
    ie
    0.94
     volver
    0.94
    ä
    0.91
    Act Density 0.002%

    No Known Activations