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
    Una
    -0.07
     pokus
    -0.06
     доч
    -0.06
     captcha
    -0.06
     Payne
    -0.06
     обмеж
    -0.06
    nic
    -0.06
     Nash
    -0.06
    Abr
    -0.06
    position
    -0.06
    POSITIVE LOGITS
     World
    0.12
     world
    0.12
     WORLD
    0.12
    World
    0.10
     worlds
    0.09
    .World
    0.09
    -world
    0.09
    .world
    0.08
     Worlds
    0.08
    (World
    0.08
    Act Density 0.065%

    No Known Activations