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

    Neuronpedia

    INDEX
    Explanations

    education systems and importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.27
    وم
    1.15
    ിയ
    1.13
    '
    1.07
    1.06
    وت
    1.04
     různých
    1.04
     europeo
    1.01
    。
    1.00
    ۔
    0.98
    POSITIVE LOGITS
    0
    1.82
    ;
    1.68
    ۰
    1.66
    ０
    1.60
    ן
    1.55
    an
    1.52
    р
    1.52
    a
    1.50
    )
    1.43
    n
    1.41
    Act Density 0.015%

    No Known Activations