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

    Neuronpedia

    INDEX
    Explanations

    Generative AI, neural networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Authorities
    -0.09
     authorities
    -0.09
     embrace
    -0.09
     injust
    -0.08
    ��
    -0.08
     embraced
    -0.08
     brakes
    -0.08
     esfuerzos
    -0.08
     injustice
    -0.08
     joys
    -0.08
    POSITIVE LOGITS
    生成
    0.16
     génération
    0.15
     generating
    0.14
     generación
    0.14
    .generate
    0.14
     geração
    0.13
     generation
    0.13
     gerar
    0.13
     generar
    0.13
     генера
    0.12
    Act Density 0.018%

    No Known Activations