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

    Neuronpedia

    INDEX
    Explanations

    additionally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    见
    -0.08
    verting
    -0.07
     Gör
    -0.07
     optics
    -0.07
     gider
    -0.07
    .Iterator
    -0.07
    卸
    -0.07
     Gou
    -0.07
    .Profile
    -0.07
    ientes
    -0.07
    POSITIVE LOGITS
     prohibited
    0.11
     requisito
    0.09
     соблюдать
    0.09
     banned
    0.09
     mandated
    0.09
    Requirements
    0.09
     شرط
    0.09
     запрещ
    0.09
     REQUIRE
    0.09
     verplicht
    0.09
    Act Density 0.034%

    No Known Activations