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

    Neuronpedia

    INDEX
    Explanations

    foreign words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Debido
    1.03
     Однако
    0.92
    IVITY
    0.91
    鏻
    0.89
     Hydrochloride
    0.89
     worded
    0.88
    你说
    0.86
     llevando
    0.86
    ﮩ
    0.86
    薁
    0.85
    POSITIVE LOGITS
    ري
    0.91
    ت
    0.88
    на
    0.87
    ки
    0.86
    مان
    0.80
    న
    0.80
    ك
    0.79
    j
    0.78
     sorgt
    0.78
    कर
    0.77
    Act Density 0.001%

    No Known Activations