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

    Neuronpedia

    INDEX
    Explanations

    game levels/puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aanleg
    -0.09
    👌
    -0.09
    -ke
    -0.08
     interesado
    -0.08
     kiinnost
    -0.08
    ರು
    -0.08
     interessado
    -0.08
    👏
    -0.08
    投稿
    -0.08
     kasance
    -0.08
    POSITIVE LOGITS
     Maze
    0.11
     भूल
    0.11
     deceptive
    0.11
     labyrinth
    0.10
     лаб
    0.10
     Puzzle
    0.09
     desafio
    0.09
    Maze
    0.09
    谜
    0.09
     Challenge
    0.09
    Act Density 0.030%

    No Known Activations