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

    Neuronpedia

    INDEX
    Explanations

    Fortran code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filmmakers
    -0.08
     attraction
    -0.08
    明星
    -0.08
     exhibitors
    -0.08
    Walter
    -0.08
     swings
    -0.08
     indie
    -0.08
     attractions
    -0.08
    植物
    -0.08
     waterfront
    -0.08
    POSITIVE LOGITS
     선언
    0.10
    Declare
    0.10
     ঘোষ
    0.09
     deklar
    0.09
     घोषणा
    0.09
     പ്രഖ്യാപ
    0.09
     declarar
    0.09
     cantar
    0.09
     declare
    0.09
     declaração
    0.09
    Act Density 0.003%

    No Known Activations