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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΩΤ
    -0.07
    aley
    -0.07
    ά
    -0.06
     Kerry
    -0.06
    ilded
    -0.06
     typingsJapgolly
    -0.06
    kara
    -0.06
     onde
    -0.06
     "}↵
    -0.06
     ',
    -0.06
    POSITIVE LOGITS
     tiếp
    0.07
    -figure
    0.07
    세요
    0.07
     منزل
    0.06
    ormap
    0.06
     　　　　　
    0.06
     dựng
    0.06
    .figure
    0.06
    (server
    0.06
     Hình
    0.06
    Act Density 0.030%

    No Known Activations