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

    Neuronpedia

    INDEX
    Explanations

    disbelief or questioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     empty
    -0.07
    鲜
    -0.07
    _books
    -0.07
    pent
    -0.07
     &[
    -0.07
    renders
    -0.07
     QLabel
    -0.06
    ıydı
    -0.06
    z
    -0.06
     Zac
    -0.06
    POSITIVE LOGITS
     main
    0.06
     dns
    0.06
     khởi
    0.05
     підстав
    0.05
    равиль
    0.05
    (PATH
    0.05
     був
    0.05
     raids
    0.05
    (ids
    0.05
     cif
    0.05
    Act Density 0.007%

    No Known Activations