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

    Neuronpedia

    INDEX
    Explanations

    要

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drum
    -0.07
     circum
    -0.07
     Rum
    -0.07
    .Repositories
    -0.07
     ClassName
    -0.06
     гли
    -0.06
    íně
    -0.06
     assms
    -0.06
    ерап
    -0.06
    .bn
    -0.06
    POSITIVE LOGITS
     toward
    0.07
    وات
    0.06
     UNKNOWN
    0.06
    ?$
    0.06
     Watt
    0.06
    	await
    0.06
    .yahoo
    0.06
    .Keyword
    0.06
    ANO
    0.06
     bucks
    0.06
    Act Density 0.003%

    No Known Activations