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

    Neuronpedia

    INDEX
    Explanations

    text related to playing sports in leagues and college

    oai_token-act-pair · gemini-2.0-flash

    soccer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    发表于
    -0.55
    脚注の使い方
    -0.53
    ByteBuf
    -0.49
    uxxxx
    -0.46
    BindView
    -0.44
    HomeAsUpEnabled
    -0.44
     uska
    -0.44
     viewDidLoad
    -0.42
    teg
    -0.42
    เก
    -0.42
    POSITIVE LOGITS
    kkue
    0.67
    Fuzz
    0.59
     समीक्षक
    0.59
     otomatig
    0.57
     tramonto
    0.56
    Халык
    0.55
     changé
    0.55
    μιουργ
    0.55
     Италијани
    0.55
     scattata
    0.54
    Act Density 1.090%

    No Known Activations