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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sentido
    -0.07
    acin
    -0.07
    akit
    -0.07
     Für
    -0.07
     droit
    -0.07
     ביום
    -0.07
    _mac
    -0.06
     mankind
    -0.06
     Huntington
    -0.06
     Eid
    -0.06
    POSITIVE LOGITS
    参与
    0.07
     ans
    0.07
    ")}↵
    0.07
    loys
    0.07
     challenged
    0.07
    ple
    0.07
    启动
    0.07
     adjusted
    0.06
    凑
    0.06
    ключение
    0.06
    Act Density 0.013%

    No Known Activations