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
     messa
    0.70
     egensk
    0.70
     atributo
    0.69
     einger
    0.69
     router
    0.68
    GON
    0.67
     بالوں
    0.67
     nuisance
    0.66
    विभाग
    0.65
    Dots
    0.65
    POSITIVE LOGITS
     WWII
    3.20
     wartime
    2.57
     war
    2.45
     WW
    2.23
     World
    2.20
    WW
    2.13
     War
    2.12
     Nazi
    2.11
     wars
    2.08
    War
    2.05
    Act Density 0.125%

    No Known Activations