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

    Neuronpedia

    INDEX
    Explanations

    more than and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.38
    很有
    0.34
     很
    0.33
    。
    0.32
     매우
    0.32
     очень
    0.31
    是很
    0.31
    any
    0.31
     بكل
    0.31
    鋐
    0.31
    POSITIVE LOGITS
     than
    0.83
     niż
    0.78
     kuin
    0.63
     чем
    0.62
    Than
    0.60
     decât
    0.60
    than
    0.59
     allá
    0.58
     než
    0.57
     Than
    0.52
    Act Density 0.052%

    No Known Activations