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

    Neuronpedia

    INDEX
    Explanations

    models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Its
    -0.07
    Its
    -0.07
    .sim
    -0.06
    ,**
    -0.06
     Flex
    -0.06
    _Server
    -0.06
     About
    -0.06
     tủ
    -0.06
    ­tion
    -0.06
     deben
    -0.06
    POSITIVE LOGITS
    mw
    0.07
     FUNCTIONS
    0.07
    _friends
    0.06
    redentials
    0.06
    aydı
    0.06
    openh
    0.06
    _MON
    0.06
     PyTuple
    0.06
    ẹn
    0.06
     دستگاه
    0.06
    Act Density 0.253%

    No Known Activations