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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rempl
    -0.07
     комплек
    -0.06
     rookies
    -0.06
     geçmiş
    -0.06
    hek
    -0.06
     obed
    -0.06
     partes
    -0.06
    Simple
    -0.06
    寻
    -0.06
     通
    -0.06
    POSITIVE LOGITS
     зі
    0.07
     Gender
    0.06
    ώρα
    0.06
    fadeOut
    0.06
    ····
    0.06
     Minority
    0.06
     VID
    0.06
     dollars
    0.06
    انگ
    0.06
     açıklam
    0.06
    Act Density 0.051%

    No Known Activations