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

    Neuronpedia

    INDEX
    Explanations

    publication details and ISBNs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cooldown
    0.37
     backsplash
    0.35
     chuva
    0.35
     onboarding
    0.34
     planar
    0.34
     approu
    0.33
     webhook
    0.33
     véhicules
    0.33
     charlas
    0.33
     animación
    0.33
    POSITIVE LOGITS
     Books
    0.57
     ISBN
    0.55
     paperback
    0.54
    ISBN
    0.53
    Books
    0.52
    isbn
    0.50
     Paperback
    0.49
     Publishers
    0.48
     Publisher
    0.48
    图书
    0.47
    Act Density 0.006%

    No Known Activations