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

    Neuronpedia

    INDEX
    Explanations

    certainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ULT
    -0.07
     narrower
    -0.06
    lder
    -0.06
     기본
    -0.06
    .lower
    -0.06
    Sunday
    -0.06
     arrows
    -0.06
    	min
    -0.06
    oS
    -0.06
    _BUSY
    -0.06
    POSITIVE LOGITS
    ินทาง
    0.06
     senha
    0.06
    部门
    0.06
    аблиц
    0.06
    opensource
    0.06
     Vogue
    0.06
    htdocs
    0.06
     diced
    0.06
    :'↵
    0.06
    jong
    0.06
    Act Density 0.141%

    No Known Activations