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

    Neuronpedia

    INDEX
    Explanations

    news sources and networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.88
    <0x0D>
    0.83
     It
    0.79
    If
    0.75
    ↵
    0.73
    It
    0.70
    um
    0.69
    In
    0.69
    ม
    0.68
    ：
    0.66
    POSITIVE LOGITS
    사
    0.89
    ου
    0.80
    дцать
    0.70
    сколько
    0.68
    ⺊
    0.67
    つの
    0.65
     hapless
    0.64
     subtração
    0.64
    ಕ್
    0.64
    cible
    0.64
    Act Density 0.009%

    No Known Activations