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

    Neuronpedia

    INDEX
    Explanations

    life and soul

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    من
    0.52
    وم
    0.52
    ova
    0.48
     ساعات
    0.46
    يا
    0.45
     innovator
    0.45
     島
    0.45
    س
    0.44
     போட்ட
    0.44
     اول
    0.44
    POSITIVE LOGITS
    Jlc
    0.59
    価値
    0.51
    кр
    0.47
     करूंगा
    0.47
     sesize
    0.47
     Huz
    0.46
     fatigue
    0.46
     CORPER
    0.45
     ആണ
    0.45
    ᗜ
    0.45
    Act Density 0.000%

    No Known Activations