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

    Neuronpedia

    INDEX
    Explanations

    Assignment operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     щ
    -0.06
     prejudices
    -0.06
    -double
    -0.06
    iggs
    -0.06
     soothing
    -0.06
     através
    -0.06
     уяв
    -0.05
     rağmen
    -0.05
     politic
    -0.05
     않았다
    -0.05
    POSITIVE LOGITS
     tarihli
    0.07
     USE
    0.07
    locations
    0.07
     happens
    0.07
    回
    0.06
     stopping
    0.06
    .Man
    0.06
     originally
    0.06
     сдел
    0.06
    ительным
    0.06
    Act Density 0.023%

    No Known Activations