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

    Neuronpedia

    INDEX
    Explanations

    Car engine parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prohibited
    -0.08
     mirror
    -0.08
    襲
    -0.07
    可在
    -0.07
    Dispatch
    -0.07
    -inverse
    -0.07
    covering
    -0.07
     precisely
    -0.07
     mogelijk
    -0.07
    可想
    -0.07
    POSITIVE LOGITS
    长辈
    0.07
     Hor
    0.07
     thats
    0.07
    岁以上
    0.07
    上传
    0.07
    �
    0.07
    앳
    0.07
     Qi
    0.07
    ꕥ
    0.06
    ㈰
    0.06
    Act Density 0.013%

    No Known Activations