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

    Neuronpedia

    INDEX
    Explanations

    10

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Printer
    -0.08
     бу
    -0.08
     pictures
    -0.07
     decoration
    -0.07
    Бу
    -0.07
     outpatient
    -0.07
     निर्देशक
    -0.07
     Бу
    -0.07
    ьи
    -0.07
     gripping
    -0.07
    POSITIVE LOGITS
     প্রকাশ
    0.08
     Ny
    0.08
     svog
    0.07
    (storage
    0.07
    せ
    0.07
    Ny
    0.07
     പ്ര
    0.07
    [level
    0.07
    {x
    0.07
    _temp
    0.07
    Act Density 0.007%

    No Known Activations