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

    Neuronpedia

    INDEX
    Explanations

    wars, revolutions, and crises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     occasionally
    0.38
     မိ
    0.37
    操作系统
    0.37
     Occasionally
    0.36
     LinearLayout
    0.36
     অপারেটিং
    0.35
     উপাদান
    0.35
     seedlings
    0.34
    Occasionally
    0.34
     pojem
    0.34
    POSITIVE LOGITS
     crisis
    0.98
     wars
    0.96
     rebellion
    0.94
     guerras
    0.93
     guerra
    0.91
     riots
    0.91
     upheaval
    0.90
     revolt
    0.89
     outbreak
    0.88
     uprising
    0.86
    Act Density 0.058%

    No Known Activations