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

    Neuronpedia

    INDEX
    Explanations

    distributed computing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    念头
    -0.08
    粉碎
    -0.07
    ,W
    -0.07
     mane
    -0.07
     shove
    -0.07
    amar
    -0.07
    Cipher
    -0.07
    يز
    -0.07
    ewish
    -0.07
     Seamless
    -0.07
    POSITIVE LOGITS
     variables
    0.08
     будет
    0.07
     关
    0.07
    共同努力
    0.07
     customers
    0.07
    굶
    0.07
    ř
    0.06
    ",
↵
    0.06
    高压
    0.06
    实际情况
    0.06
    Act Density 0.023%

    No Known Activations