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

    Neuronpedia

    INDEX
    Explanations

    giving examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moreover
    0.47
     પરંતુ
    0.44
     furthermore
    0.43
     additionally
    0.43
     परंतु
    0.41
     Inoltre
    0.40
    لیکن
    0.40
     namun
    0.39
     எனவே
    0.39
     لیکن
    0.39
    POSITIVE LOGITS
     например
    0.83
     مثلا
    0.81
     misalnya
    0.75
     Например
    0.75
    比如
    0.71
    たとえば
    0.70
     bijvoorbeeld
    0.68
    例えば
    0.68
    比如說
    0.66
     Misalnya
    0.66
    Act Density 1.998%

    No Known Activations