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

    Neuronpedia

    INDEX
    Explanations

    world or global issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ні
    1.09
    ਰ
    0.98
    ون
    0.92
    ە
    0.92
    ર
    0.91
    мо
    0.89
    وا
    0.88
    ار
    0.85
    ها
    0.82
    тин
    0.80
    POSITIVE LOGITS
     engulfed
    1.00
     entier
    0.96
     piena
    0.96
    ளாவ
    0.93
     entière
    0.88
    VIEW
    0.80
     devoid
    0.79
    WIDE
    0.79
    적으로
    0.75
    ̀nh
    0.75
    Act Density 0.428%

    No Known Activations