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

    Neuronpedia

    INDEX
    Explanations

    .min

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RK
    -0.08
    ерами
    -0.07
    shapes
    -0.07
     Queens
    -0.07
     thief
    -0.07
    ribbon
    -0.07
    Higher
    -0.06
     Cult
    -0.06
     interpolate
    -0.06
    :"↵
    -0.06
    POSITIVE LOGITS
     Yap
    0.07
    	ORDER
    0.06
     Madden
    0.06
    .MapFrom
    0.06
    .Xna
    0.06
    hg
    0.06
     DataContext
    0.06
    .ResponseWriter
    0.06
    settings
    0.06
     الأس
    0.06
    Act Density 0.001%

    No Known Activations