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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     susceptibles
    -0.09
     greatness
    -0.09
     Хотя
    -0.08
    @Named
    -0.08
     поводу
    -0.08
    ��
    -0.08
    retanto
    -0.08
    ㅠ
    -0.08
     Alas
    -0.08
     Embora
    -0.08
    POSITIVE LOGITS
     versatility
    0.10
     flexibility
    0.10
     reputation
    0.09
     multilingual
    0.09
     hassle
    0.09
     timely
    0.09
     versatile
    0.09
     जल
    0.09
     bilingual
    0.09
     unparalleled
    0.09
    Act Density 0.077%

    No Known Activations