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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ระยะเวลา
    -0.07
    激动
    -0.07
    啐
    -0.07
    唯美
    -0.07
    镇党委
    -0.07
    倒是
    -0.07
    不适
    -0.07
    艽
    -0.06
    审议
    -0.06
    瞄
    -0.06
    POSITIVE LOGITS
     Region
    0.07
    Province
    0.07
    Fish
    0.07
     bear
    0.07
    -directory
    0.07
    CAN
    0.07
    .restaurant
    0.07
    unicorn
    0.07
     SHOP
    0.06
    _fire
    0.06
    Act Density 0.003%

    No Known Activations