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

    Neuronpedia

    INDEX
    Explanations

    demonstratives followed by plural nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legislation
    0.50
    legislation
    0.50
     Legislation
    0.49
     ONE
    0.43
     छोटा
    0.42
     mnoho
    0.41
     qualche
    0.41
    one
    0.40
     Footage
    0.38
     оборудование
    0.38
    POSITIVE LOGITS
    这些
    0.48
    Estos
    0.48
     setups
    0.46
     things
    0.46
     kinds
    0.46
     şeyler
    0.46
     structures
    0.46
     gems
    0.44
    這些
    0.43
     beauties
    0.43
    Act Density 0.035%

    No Known Activations