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

    Neuronpedia

    INDEX
    Explanations

    memory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    udala
    -0.10
     сердце
    -0.08
    (Common
    -0.08
    _COMMON
    -0.08
     unanimous
    -0.08
     হৃদ
    -0.08
     знамен
    -0.08
     sane
    -0.07
    /router
    -0.07
     coração
    -0.07
    POSITIVE LOGITS
     정보를
    0.09
     étrangers
    0.09
     المعلومات
    0.08
     pers
    0.08
    -check
    0.08
     πληροφο
    0.08
     collectibles
    0.08
    ä
    0.08
    리에
    0.08
     التفاصيل
    0.08
    Act Density 0.008%

    No Known Activations