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

    Neuronpedia

    INDEX
    Explanations

    World War II

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raid
    0.37
    త
    0.37
    ᒐ
    0.37
     Raid
    0.36
     steady
    0.36
     Steady
    0.36
    ジット
    0.35
     উদ্ভিদ
    0.35
     ಅಂಶ
    0.35
    ষ্টার
    0.35
    POSITIVE LOGITS
     World
    1.05
    World
    0.95
     WWII
    0.90
     वर्ल्ड
    0.83
     wars
    0.82
     guerras
    0.82
     WORLD
    0.81
    戦争
    0.79
     Weltkrieg
    0.79
     мировой
    0.77
    Act Density 0.012%

    No Known Activations