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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     край
    -0.08
     задан
    -0.08
     принимает
    -0.08
     перечис
    -0.08
     принимать
    -0.08
     сочет
    -0.08
     миров
    -0.07
     аналог
    -0.07
     उन्ह
    -0.07
     принима
    -0.07
    POSITIVE LOGITS
    (TAG
    0.09
     disponibilidade
    0.08
     fath
    0.08
     scint
    0.08
     deaths
    0.07
     dahulu
    0.07
    YT
    0.07
     Availability
    0.07
    (Tag
    0.07
    Availability
    0.07
    Act Density 0.001%

    No Known Activations