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

    Neuronpedia

    INDEX
    Explanations

    by the book

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cannon
    0.38
    Rés
    0.38
    ᓐ
    0.38
     शक्तिशाली
    0.37
    Ner
    0.37
     теста
    0.37
    ิง
    0.37
     নেবার
    0.37
    Sear
    0.37
    एक्स
    0.36
    POSITIVE LOGITS
     Book
    0.60
     book
    0.57
     boek
    0.56
    Book
    0.53
     libro
    0.52
     книге
    0.52
     descrizione
    0.52
     besch
    0.50
     Libro
    0.48
    book
    0.48
    Act Density 0.000%

    No Known Activations