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

    Neuronpedia

    INDEX
    Explanations

    order of operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    teil
    -0.07
     Най
    -0.07
     convey
    -0.06
    规范
    -0.06
    nodoc
    -0.06
     зависимости
    -0.06
    nahme
    -0.06
     Вер
    -0.06
    .fasterxml
    -0.06
     Ming
    -0.06
    POSITIVE LOGITS
    admin
    0.07
     retrospect
    0.07
     adjusted
    0.06
    рити
    0.06
    empt
    0.06
    .sensor
    0.06
    kb
    0.06
    vents
    0.06
    DownList
    0.06
    akis
    0.06
    Act Density 0.013%

    No Known Activations