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

    Neuronpedia

    INDEX
    Explanations

    world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーズ
    -0.07
     безопасности
    -0.06
    [test
    -0.06
     xl
    -0.06
     pomoci
    -0.06
     Stud
    -0.06
     André
    -0.06
     مذ
    -0.06
     mật
    -0.06
     Mormons
    -0.06
    POSITIVE LOGITS
     world
    0.11
     World
    0.09
     wereld
    0.07
    World
    0.07
     '::
    0.07
     世界
    0.06
     мир
    0.06
    世界
    0.06
     recipient
    0.06
     WORLD
    0.06
    Act Density 0.025%

    No Known Activations