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

    Neuronpedia

    INDEX
    Explanations

    educational purposes and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不仅
    1.14
    不仅仅
    1.13
     також
    1.11
     cũng
    1.11
    也
    1.10
     również
    1.10
     също
    1.09
     بھی
    1.05
     тоже
    1.03
    除了
    1.00
    POSITIVE LOGITS
    而已
    1.27
     saja
    1.22
     thôi
    1.21
     sahaja
    1.02
    罢了
    0.95
    เท่านั้น
    0.91
     ही
    0.81
     lamang
    0.77
     ਹੀ
    0.74
     나머
    0.69
    Act Density 0.137%

    No Known Activations