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

    Neuronpedia

    INDEX
    Explanations

    Parentheses and curly braces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     missionary
    -0.09
     Tā
    -0.09
     Mika
    -0.08
     Providing
    -0.08
     Eric
    -0.08
     missionaries
    -0.08
     Incorpor
    -0.07
     Deniz
    -0.07
     Erk
    -0.07
    847
    -0.07
    POSITIVE LOGITS
    Factories
    0.08
     voorstel
    0.08
     voordeel
    0.08
     вперед
    0.08
     자기
    0.07
    도로
    0.07
     물
    0.07
     platter
    0.07
     legít
    0.07
     법
    0.07
    Act Density 0.040%

    No Known Activations