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

    Neuronpedia

    INDEX
    Explanations

    quotation marks/dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     процесс
    -0.07
    ir
    -0.06
       
    -0.06
    クセ
    -0.06
    fra
    -0.06
     ####
    -0.06
    \Migrations
    -0.06
    ンド
    -0.06
     fame
    -0.06
     Bravo
    -0.06
    POSITIVE LOGITS
     nominees
    0.08
     Factory
    0.07
    �除
    0.07
    _exports
    0.07
    ůvodu
    0.06
    mmo
    0.06
    -du
    0.06
    ования
    0.06
     Document
    0.06
     FactoryGirl
    0.06
    Act Density 0.006%

    No Known Activations