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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,private
    -0.07
     vẫn
    -0.06
    �
    -0.06
    保持
    -0.06
    <Resource
    -0.06
    Mgr
    -0.06
    最
    -0.06
    国内
    -0.06
    inheritdoc
    -0.06
    ,…
    -0.06
    POSITIVE LOGITS
    TEL
    0.07
    ุษ
    0.07
    щих
    0.07
    egt
    0.07
    ynamic
    0.07
    τοι
    0.07
    iguiente
    0.07
    RP
    0.06
     atl
    0.06
    ـل
    0.06
    Act Density 0.634%

    No Known Activations