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

    Neuronpedia

    INDEX
    Explanations

    using System or Microsoft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.78
    is
    0.77
    r
    0.70
    z
    0.67
    t
    0.66
    ir
    0.64
    or
    0.63
    Middle
    0.63
    '
    0.62
    p
    0.61
    POSITIVE LOGITS
     내부
    0.63
     설치
    0.61
     화학
    0.60
    ޟ
    0.59
    कुर
    0.58
     نیست
    0.58
     노
    0.57
     عمل
    0.57
     ساعة
    0.57
     다양한
    0.56
    Act Density 0.000%

    No Known Activations