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

    Neuronpedia

    INDEX
    Explanations

    ress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '{{
    -0.07
     efficient
    -0.07
     иму
    -0.06
     Shelter
    -0.06
     гид
    -0.06
     mer
    -0.06
     zona
    -0.06
     dbName
    -0.06
     králov
    -0.06
    ิดต
    -0.06
    POSITIVE LOGITS
    escription
    0.07
    ressing
    0.06
    ,long
    0.06
    =F
    0.06
    =↵
    0.06
     nhất
    0.06
    .AWS
    0.06
    raised
    0.06
     actors
    0.06
    ۲۰۲
    0.06
    Act Density 0.006%

    No Known Activations