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

    Neuronpedia

    INDEX
    Explanations

    keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acompanhamento
    -0.08
    -0.07
    क्षम
    -0.07
     оны
    -0.07
     recomendado
    -0.07
    аста
    -0.07
     вариант
    -0.07
    .Send
    -0.07
    ）は
    -0.07
     opção
    -0.07
    POSITIVE LOGITS
     keywords
    0.11
     clues
    0.11
    关键词
    0.11
    Keywords
    0.09
    notice
    0.09
    keywords
    0.09
     nouns
    0.09
     pistas
    0.09
     Keywords
    0.09
     hints
    0.08
    Act Density 0.008%
    No Known Activations