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

    Neuronpedia

    INDEX
    Explanations

    E

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FML
    -0.06
    ursal
    -0.06
    .ButterKnife
    -0.06
     організа
    -0.06
    。それ
    -0.06
     bubbles
    -0.06
     Brown
    -0.06
     confusion
    -0.06
     Explain
    -0.06
    Compar
    -0.05
    POSITIVE LOGITS
     yönetim
    0.07
     đem
    0.07
    ické
    0.07
     війни
    0.06
     따른
    0.06
     zá
    0.06
    cuda
    0.06
     Serge
    0.06
    수로
    0.06
    IGNED
    0.06
    Act Density 0.002%

    No Known Activations