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

    Neuronpedia

    INDEX
    Explanations

    games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    せて
    0.39
    ("--
    0.37
    ervices
    0.37
     hizmet
    0.37
    鏝
    0.37
    Addressing
    0.36
     Addressing
    0.36
     sympathetic
    0.35
     fem
    0.35
    尊敬
    0.35
    POSITIVE LOGITS
     games
    1.79
     game
    1.72
     게임
    1.66
    ゲーム
    1.65
    游戏的
    1.61
    遊戲
    1.55
     juegos
    1.54
     juego
    1.52
     игры
    1.52
    게임
    1.52
    Act Density 0.024%

    No Known Activations