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

    Neuronpedia

    INDEX
    Explanations

    ISBN numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     관
    0.81
     lysis
    0.79
     ஹீ
    0.78
     ஊ
    0.76
    >=
    0.72
     SUSY
    0.70
     ServiceNow
    0.70
     bottlenecks
    0.70
     হলিউ
    0.68
    зь
    0.68
    POSITIVE LOGITS
     ISBN
    2.19
    ISBN
    2.02
    isbn
    1.92
     book
    1.87
    Book
    1.82
     paperback
    1.80
    图书
    1.75
     isbn
    1.74
     bookstores
    1.74
     Book
    1.72
    Act Density 0.181%

    No Known Activations