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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     администрации
    -0.08
     разработки
    -0.08
    ಂಡ
    -0.08
     winning
    -0.07
     сфере
    -0.07
    ాంట
    -0.07
     автор
    -0.07
    Winning
    -0.07
     правительства
    -0.07
     приобрет
    -0.07
    POSITIVE LOGITS
     Karin
    0.08
     pacientes
    0.07
    Rose
    0.07
    adara
    0.07
    alph
    0.07
     zak
    0.07
     mov
    0.07
     líquidos
    0.07
     ZE
    0.07
    ajaj
    0.07
    Act Density 0.001%

    No Known Activations