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
     world
    -1.38
    world
    -1.07
     WORLD
    -1.06
     World
    -1.01
    World
    -0.91
    WORLD
    -0.89
     세계
    -0.89
    ^(@)
    -0.84
     Welt
    -0.82
     wereld
    -0.82
    POSITIVE LOGITS
    ly
    0.61
    wide
    0.58
    ваемых
    0.56
    WIDE
    0.53
    ally
    0.52
    y
    0.51
     of
    0.48
    a
    0.47
    r
    0.47
    ingly
    0.47
    Act Density 1.125%

    No Known Activations