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

    Neuronpedia

    INDEX
    Explanations

    such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BUSINESS
    0.44
     specialist
    0.43
     dispatch
    0.41
     tiden
    0.40
     tổng
    0.39
     всі
    0.39
     Archim
    0.39
    കളും
    0.38
     edit
    0.38
     ration
    0.37
    POSITIVE LOGITS
    わけで
    0.46
     بحيث
    0.43
     Namely
    0.43
    说法
    0.43
     funniest
    0.42
     например
    0.42
    কী
    0.41
     ώστε
    0.39
     څنګه
    0.38
     ホワイト
    0.38
    Act Density 0.003%

    No Known Activations