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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kas
    0.47
     многочис
    0.42
     ops
    0.40
     cas
    0.40
    肅
    0.39
     STAFF
    0.39
    Kas
    0.38
     diligent
    0.38
     популярных
    0.38
    ılması
    0.38
    POSITIVE LOGITS
    haupt
    0.42
    raulic
    0.41
    Fro
    0.41
    shelf
    0.40
    ുകൊണ്ട്
    0.40
    games
    0.38
     Fro
    0.38
    carbonate
    0.38
     shelf
    0.37
    ding
    0.37
    Act Density 0.000%

    No Known Activations