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

    Neuronpedia

    INDEX
    Explanations

    regular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     excludes
    -0.07
    汚れ
    -0.07
    *)(
    -0.07
    .*?)
    -0.07
     sust
    -0.07
    BSITE
    -0.07
    коль
    -0.06
    istribution
    -0.06
    rb
    -0.06
    することで
    -0.06
    POSITIVE LOGITS
     {!
    0.07
     Tested
    0.07
    	Size
    0.07
     poured
    0.06
     Stocks
    0.06
     '↵
    0.06
     mmap
    0.06
     (_.
    0.06
    獻
    0.06
     hero
    0.06
    Act Density 0.100%

    No Known Activations