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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extrav
    -0.07
     등록대행
    -0.06
    усти
    -0.06
     آسی
    -0.06
     interrupted
    -0.06
     konuş
    -0.06
    。↵
    -0.06
    ações
    -0.06
     INFORMATION
    -0.06
     чер
    -0.06
    POSITIVE LOGITS
     Dominic
    0.07
    ,Th
    0.06
     بنی
    0.06
     signup
    0.06
     yeter
    0.06
     Keto
    0.06
     "==
    0.06
    영
    0.06
    �
    0.06
     Sylv
    0.06
    Act Density 0.004%

    No Known Activations