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

    Neuronpedia

    INDEX
    Explanations

    technical questions and answers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    隧
    -0.07
    �
    -0.07
    Ur
    -0.06
     �
    -0.06
    新生
    -0.06
    (startDate
    -0.06
    vine
    -0.06
    有必要
    -0.06
    没事
    -0.06
    멍
    -0.06
    POSITIVE LOGITS
    的数量
    0.07
    alogy
    0.07
     prophet
    0.07
    ocation
    0.07
    Making
    0.07
    raising
    0.06
    ünkü
    0.06
    irate
    0.06
    (calendar
    0.06
    更多
    0.06
    Act Density 0.201%

    No Known Activations