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

    Neuronpedia

    INDEX
    Explanations

    overall summary of trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     someday
    0.54
     eventually
    0.51
     manchmal
    0.48
     Optionally
    0.48
     eventualmente
    0.47
     सक्षम
    0.47
     optionally
    0.47
     someone
    0.46
     suppose
    0.46
     Ведь
    0.45
    POSITIVE LOGITS
    Overall
    0.84
     Overall
    0.82
    整體
    0.79
     overall
    0.77
     notable
    0.77
    overall
    0.77
    despite
    0.75
     despite
    0.71
     Interestingly
    0.71
    总体
    0.71
    Act Density 0.050%

    No Known Activations