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

    Neuronpedia

    INDEX
    Explanations

    founded or co-founded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pursue
    0.50
    ق
    0.45
    niji
    0.43
    purs
    0.42
    人民币
    0.42
     upaya
    0.41
    maintain
    0.41
    nije
    0.41
    tsy
    0.40
    녓
    0.40
    POSITIVE LOGITS
     داده
    0.47
    訖
    0.43
    ụng
    0.42
     unim
    0.42
     stochastic
    0.41
     મદ
    0.41
    )\
    0.41
     fmt
    0.40
    ErrorInfo
    0.40
    Parameterized
    0.39
    Act Density 0.000%

    No Known Activations