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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ngành
    -0.07
    (clone
    -0.07
    ünst
    -0.07
    클
    -0.07
    abbreviation
    -0.07
    今年以来
    -0.07
     watts
    -0.07
    olders
    -0.07
    uple
    -0.07
    edics
    -0.06
    POSITIVE LOGITS
     NA
    0.07
     McKin
    0.07
    smtp
    0.07
     disappearing
    0.07
     พฤษภา
    0.07
     Martha
    0.06
    总会
    0.06
     Prevent
    0.06
     значит
    0.06
     dropped
    0.06
    Act Density 0.002%

    No Known Activations