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

    Neuronpedia

    INDEX
    Explanations

    world 's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fourier
    -0.06
    Ax
    -0.06
     naz
    -0.06
    erson
    -0.06
    Aud
    -0.06
     AUTH
    -0.06
    出品者
    -0.05
     Forward
    -0.05
    .Ui
    -0.05
     Cour
    -0.05
    POSITIVE LOGITS
     world
    0.11
     World
    0.08
     mundial
    0.07
     банк
    0.07
    .unsqueeze
    0.07
     rely
    0.07
    ORLD
    0.07
    инок
    0.07
     WORLD
    0.07
    //"
    0.07
    Act Density 0.084%

    No Known Activations