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

    Neuronpedia

    INDEX
    Explanations

    comparisons with than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mies
    0.39
    ંટ
    0.39
    냈다
    0.39
    anges
    0.38
    िलेश
    0.38
    ïdes
    0.38
    rcParams
    0.38
    kish
    0.37
    rição
    0.37
    RIER
    0.37
    POSITIVE LOGITS
     than
    1.09
     kuin
    0.90
     než
    0.86
     decât
    0.80
     Than
    0.80
    Than
    0.78
     niż
    0.77
    than
    0.74
    กว่า
    0.73
     än
    0.66
    Act Density 0.031%

    No Known Activations