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

    Neuronpedia

    INDEX
    Explanations

    multilingual business concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可以
    0.52
     可以
    0.47
     able
    0.44
    可
    0.43
    也可以
    0.42
     如果
    0.42
     Able
    0.42
    (`#
    0.41
     इन
    0.41
    其他
    0.41
    POSITIVE LOGITS
    냅
    0.43
     বৎসর
    0.41
     acidity
    0.40
     فهو
    0.40
    憔
    0.40
     bisque
    0.39
     Forecasting
    0.39
     Britannia
    0.38
    whenever
    0.38
     निरंतर
    0.38
    Act Density 0.002%

    No Known Activations