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

    Neuronpedia

    INDEX
    Explanations

    God of War Ragnarök

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    乐趣
    0.39
     போல
    0.39
     unmarked
    0.39
    开口
    0.38
    ശ്ച
    0.38
    Benzoimidazol
    0.38
     thrombo
    0.38
    gunakan
    0.37
    incia
    0.36
    toires
    0.35
    POSITIVE LOGITS
     vod
    0.40
    His
    0.39
     Redeem
    0.39
     His
    0.36
     State
    0.35
     apareció
    0.35
     cay
    0.35
    ដ
    0.35
     mạng
    0.35
     film
    0.34
    Act Density 0.001%

    No Known Activations