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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Word
    -0.07
    พระราช
    -0.07
     Holidays
    -0.07
     multiprocessing
    -0.06
    {↵↵↵
    -0.06
    .receiver
    -0.06
    Train
    -0.06
     Patron
    -0.06
    Picture
    -0.06
     product
    -0.06
    POSITIVE LOGITS
    넷
    0.07
    ufig
    0.07
    óln
    0.07
    wan
    0.06
    lobber
    0.06
     español
    0.06
    يع
    0.06
    ponse
    0.06
    اسر
    0.06
    raně
    0.06
    Act Density 0.001%

    No Known Activations