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
     ефектив
    -0.06
    .AddItem
    -0.06
     noises
    -0.06
     éxito
    -0.06
    Ethernet
    -0.06
     мень
    -0.06
    engin
    -0.06
     لا
    -0.06
     penetration
    -0.06
     άλλ
    -0.06
    POSITIVE LOGITS
     World
    0.15
    World
    0.13
    world
    0.09
     world
    0.08
     WORLD
    0.07
    -world
    0.07
    (World
    0.07
    .World
    0.06
    WND
    0.06
    �습니다
    0.06
    Act Density 0.015%

    No Known Activations