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

    Neuronpedia

    INDEX
    Explanations

    place at the time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viena
    -1.83
     vienas
    -1.77
     kasama
    -1.59
     papild
    -1.49
     hvilken
    -1.48
     kapag
    -1.45
     lamang
    -1.40
     habang
    -1.38
     pirm
    -1.37
     noong
    -1.34
    POSITIVE LOGITS
     at
    9.63
    At
    3.19
     At
    2.67
     tại
    2.45
    此时
    2.33
    at
    2.09
     lúc
    1.93
    Tại
    1.91
     عند
    1.84
    此時
    1.84
    Act Density 0.511%

    No Known Activations