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

    Neuronpedia

    INDEX
    Explanations

    labyrinths and mazes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "</
    -0.06
    conexion
    -0.06
     Bugün
    -0.06
     Stored
    -0.06
     original
    -0.06
     foto
    -0.06
    promo
    -0.06
     fishermen
    -0.06
     pueblo
    -0.06
    BackingField
    -0.06
    POSITIVE LOGITS
     labyrinth
    0.15
     maze
    0.14
     Maze
    0.13
    abyrin
    0.10
    abyrinth
    0.10
    maze
    0.08
    iž
    0.07
     gy
    0.06
     devoid
    0.06
    _puts
    0.06
    Act Density 0.002%

    No Known Activations