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

    Neuronpedia

    INDEX
    Explanations

    lists, orders, and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    డ్‌
    0.42
     florals
    0.41
    нер
    0.40
    時候
    0.39
     ছন্দ
    0.39
    ब
    0.38
     watersheds
    0.38
    Фор
    0.38
     unicorns
    0.38
    బర్
    0.37
    POSITIVE LOGITS
    Approx
    0.44
    Contin
    0.44
     prend
    0.44
    立场
    0.43
    isphere
    0.42
     Vivekan
    0.42
     facie
    0.42
     evacuated
    0.41
     suje
    0.41
     atteggi
    0.41
    Act Density 0.014%

    No Known Activations