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

    Neuronpedia

    INDEX
    Explanations

    website pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     си
    0.37
    埶
    0.37
    OrderFlight
    0.36
     ऑर्डर
    0.36
    取る
    0.35
    スタイル
    0.35
     છેલ્લા
    0.35
     breakout
    0.35
     scall
    0.34
    שות
    0.34
    POSITIVE LOGITS
     pages
    1.50
    pages
    1.38
     Pages
    1.34
    Pages
    1.29
     page
    1.18
     PAGES
    1.18
     páginas
    1.12
    page
    1.08
     pagine
    1.08
     Page
    1.03
    Act Density 0.036%

    No Known Activations