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

    Neuronpedia

    INDEX
    Explanations

    thumbs, opposable, grip, touch, placement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ज्यादा
    0.98
     palladium
    0.97
     площадь
    0.92
    ූර්
    0.90
    蹌
    0.88
    вёр
    0.88
     schade
    0.88
     известный
    0.86
    රා
    0.85
     писатель
    0.85
    POSITIVE LOGITS
    p
    1.13
    '
    0.95
    ار
    0.93
    بن
    0.87
    ق
    0.85
    وه
    0.80
    ть
    0.80
     réun
    0.80
    ती
    0.79
     întreb
    0.79
    Act Density 0.001%

    No Known Activations