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

    Neuronpedia

    INDEX
    Explanations

    Data breaches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meaningful
    -0.07
     forgotten
    -0.07
     Entertainment
    -0.06
    apiro
    -0.06
     :)↵↵
    -0.06
    etched
    -0.06
    :↵↵
    -0.06
    .changed
    -0.06
     apt
    -0.06
    crime
    -0.06
    POSITIVE LOGITS
    SerializeField
    0.06
    abstractmethod
    0.06
    ﺪ
    0.06
     savaş
    0.06
    "fmt
    0.06
    mobile
    0.06
     beyaz
    0.06
     Ihr
    0.06
    kuk
    0.06
    [string
    0.06
    Act Density 0.034%

    No Known Activations