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

    Neuronpedia

    INDEX
    Explanations

    alternatives or disjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     may
    0.40
     maybe
    0.39
    不能
    0.37
     almost
    0.37
     হয়ত
    0.37
    อาจ
    0.37
     cannot
    0.37
     কিছুটা
    0.36
     mostly
    0.36
     може
    0.36
    POSITIVE LOGITS
     veya
    0.86
     или
    0.80
     किंवा
    0.78
     alebo
    0.73
     yoki
    0.72
    หรือ
    0.71
    或其他
    0.70
     ወይም
    0.68
     ataupun
    0.68
    或
    0.68
    Act Density 0.386%

    No Known Activations