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

    Neuronpedia

    INDEX
    Explanations

    debtor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ****************
    -0.07
    他是
    -0.06
    details
    -0.06
    (zip
    -0.06
    我是
    -0.06
    STOP
    -0.06
    TRL
    -0.06
    ጥ
    -0.06
     minister
    -0.06
    放到
    -0.06
    POSITIVE LOGITS
    技术服务
    0.07
    为你
    0.07
    蜱
    0.07
    uese
    0.06
     synerg
    0.06
    _lo
    0.06
     pounded
    0.06
    (thread
    0.06
    周二
    0.06
     Shiite
    0.06
    Act Density 0.002%

    No Known Activations