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

    Neuronpedia

    INDEX
    Explanations

    break or pause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     เร
    0.69
     elegantes
    0.60
     शुल्क
    0.60
    ཏ
    0.60
     अकेले
    0.58
     سیک
    0.58
    elolaan
    0.58
    氐
    0.57
    เร
    0.56
    雛
    0.56
    POSITIVE LOGITS
     break
    3.95
     breaks
    3.62
    break
    3.54
     Break
    3.41
    Break
    3.19
     Breaks
    3.05
    breaks
    2.86
     BREAK
    2.75
     ब्रेक
    2.49
     breaking
    2.34
    Act Density 0.143%

    No Known Activations