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

    Neuronpedia

    INDEX
    Explanations

    Artificial Intelligence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    會員
    -0.09
     contendo
    -0.09
    nibus
    -0.09
     #:
    -0.09
    udya
    -0.09
     verpflicht
    -0.08
     ::↵↵
    -0.08
    Charg
    -0.08
     默
    -0.08
    零钱
    -0.08
    POSITIVE LOGITS
     menschen
    0.11
     humano
    0.11
     inteligencia
    0.10
     능
    0.10
     인간
    0.10
    能力
    0.10
     conversational
    0.10
     competence
    0.09
     inteligência
    0.09
     menselijke
    0.09
    Act Density 0.019%

    No Known Activations