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

    Neuronpedia

    INDEX
    Explanations

    ocyte

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    개발
    -0.07
     SDS
    -0.07
     especific
    -0.07
     chir
    -0.07
    Doctors
    -0.07
    %',↵
    -0.07
     quest
    -0.06
     amateur
    -0.06
    已是
    -0.06
    葰
    -0.06
    POSITIVE LOGITS
    抢劫
    0.07
    דת
    0.07
    踢
    0.07
     violence
    0.07
    _documents
    0.07
    ꦏ
    0.07
    的通知
    0.07
    מאה
    0.07
     должен
    0.07
     bondage
    0.07
    Act Density 0.002%

    No Known Activations