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

    Neuronpedia

    INDEX
    Explanations

    World

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mayor
    -0.07
    묘
    -0.07
     seem
    -0.07
    ?,↵
    -0.07
    院副院长
    -0.07
    此文
    -0.06
    /query
    -0.06
    初始化
    -0.06
    /manual
    -0.06
    enever
    -0.06
    POSITIVE LOGITS
    镳
    0.08
    Tek
    0.08
    etting
    0.07
    標
    0.07
     kup
    0.07
     talking
    0.07
     Girlfriend
    0.06
     roots
    0.06
    ...)↵
    0.06
    علامات
    0.06
    Act Density 0.003%

    No Known Activations