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

    Neuronpedia

    INDEX
    Explanations

    game terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ERISA
    0.50
     URLs
    0.49
    ណ្ឌ
    0.48
     Arzneim
    0.47
     geographical
    0.47
     относя
    0.47
     Notwithstanding
    0.46
    ěř
    0.46
     заклад
    0.46
     부동산
    0.46
    POSITIVE LOGITS
    gameOver
    0.76
     game
    0.68
    ゲーム
    0.68
    game
    0.65
    GameOver
    0.64
    pygame
    0.63
     게임
    0.63
     rotate
    0.62
    GAME
    0.62
     GameOver
    0.62
    Act Density 0.239%

    No Known Activations