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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    averse
    -0.07
    Au
    -0.07
     nguyện
    -0.07
     strav
    -0.06
    xy
    -0.06
     mô
    -0.06
     مشاهدة
    -0.06
     ViewState
    -0.06
    规
    -0.06
     fos
    -0.06
    POSITIVE LOGITS
     Then
    0.07
    .addColumn
    0.07
    -directed
    0.06
    ')+
    0.06
    esimal
    0.06
    (Symbol
    0.06
     purified
    0.06
    ']↵↵↵
    0.06
     THEN
    0.06
     ranking
    0.06
    Act Density 0.023%

    No Known Activations