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

    Neuronpedia

    INDEX
    Explanations

    over time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    쨋
    0.47
     cómodo
    0.47
    쨌
    0.46
    䇝
    0.45
     (\<
    0.45
     cómoda
    0.43
    สะดวก
    0.43
     :=\
    0.42
    CCCc
    0.42
    ဝန်
    0.42
    POSITIVE LOGITS
     over
    0.64
     page
    0.57
     graph
    0.52
     across
    0.51
     above
    0.49
     chart
    0.49
     plotted
    0.49
     for
    0.49
     even
    0.49
     shows
    0.49
    Act Density 0.000%

    No Known Activations