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

    Neuronpedia

    INDEX
    Explanations

    Mixed data types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RUS
    -0.07
    -_
    -0.07
     Engagement
    -0.07
    ображ
    -0.06
     эксплуата
    -0.06
    ินค
    -0.06
    이션
    -0.06
    一些
    -0.06
     Zoo
    -0.06
     welcoming
    -0.06
    POSITIVE LOGITS
     Schumer
    0.06
    arih
    0.06
    .FILES
    0.06
    bern
    0.06
    кая
    0.06
    pais
    0.06
     Kyoto
    0.06
    educ
    0.06
    まった
    0.06
    oucher
    0.06
    Act Density 0.000%

    No Known Activations