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

    Neuronpedia

    INDEX
    Explanations

    #include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    联盟
    -0.07
    _PICTURE
    -0.07
    废
    -0.06
    igo
    -0.06
    inux
    -0.06
     tersebut
    -0.06
     KAR
    -0.06
    W
    -0.06
     screenWidth
    -0.06
     Katy
    -0.06
    POSITIVE LOGITS
    Finding
    0.07
     offensive
    0.07
     fram
    0.06
     slip
    0.06
    _compiler
    0.06
    such
    0.06
    InteractionEnabled
    0.06
    ıf
    0.06
     mapped
    0.06
     Traff
    0.06
    Act Density 0.004%

    No Known Activations