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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qq
    -0.06
    nam
    -0.06
     quotid
    -0.06
    兒
    -0.06
    (CONFIG
    -0.06
    plus
    -0.06
    يار
    -0.06
     شخص
    -0.06
    funcs
    -0.06
    	flags
    -0.06
    POSITIVE LOGITS
     aberr
    0.07
     Feder
    0.07
     Enlight
    0.06
    -content
    0.06
     Mage
    0.06
    งหมด
    0.06
    erva
    0.06
     breadcrumb
    0.06
     angel
    0.06
     feminism
    0.06
    Act Density 0.120%

    No Known Activations