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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wrong
    -0.07
     sites
    -0.07
     websites
    -0.07
    受
    -0.07
     share
    -0.07
    _Title
    -0.06
     jedna
    -0.06
     --------------------------------
    -0.06
     процесса
    -0.06
     website
    -0.06
    POSITIVE LOGITS
    ном
    0.07
     баг
    0.07
    еле
    0.06
    วรรณ
    0.06
     fray
    0.06
    ENCIES
    0.06
     "
↵
    0.06
    린이
    0.06
     sensation
    0.06
    erial
    0.06
    Act Density 0.009%

    No Known Activations