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

    Neuronpedia

    INDEX
    Explanations

    war and conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surveillance
    0.84
     stealth
    0.82
     mật
    0.80
     확보
    0.79
     interrogation
    0.76
     보안
    0.76
     intelligence
    0.71
    쇄
    0.71
     plan
    0.71
     topology
    0.70
    POSITIVE LOGITS
    战争
    1.80
     guerra
    1.74
    戦争
    1.71
     war
    1.67
     wars
    1.62
     guerras
    1.61
    戰爭
    1.59
    War
    1.56
     War
    1.56
     전쟁
    1.55
    Act Density 0.132%

    No Known Activations