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

    Neuronpedia

    INDEX
    Explanations

    global scope or scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    1.63
    ار
    1.55
    های
    1.52
    ным
    1.45
    ર
    1.42
    ال
    1.41
    ні
    1.41
    ون
    1.37
    ২
    1.23
    тин
    1.23
    POSITIVE LOGITS
     engulfed
    1.35
     entier
    1.32
     اجمع
    1.27
    ளாவ
    1.20
     entière
    1.19
    mero
    1.15
     acclaimed
    1.15
     அளவில்
    1.15
     وعند
    1.15
    VIEW
    1.13
    Act Density 0.148%

    No Known Activations