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

    Neuronpedia

    INDEX
    Explanations

    preposition World War

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     War
    1.28
     war
    1.25
    War
    1.23
     전쟁
    1.15
     guerra
    1.14
    war
    1.02
     Guerra
    1.00
    战争
    0.99
    戦争
    0.99
    战
    0.98
    POSITIVE LOGITS
     World
    0.97
    World
    0.87
     WORLD
    0.77
     Première
    0.75
     First
    0.71
    互联网档案馆
    0.66
     Primera
    0.66
     ValueTask
    0.65
    Ｗ
    0.65
    ैक्ट
    0.65
    Act Density 0.010%

    No Known Activations