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

    Neuronpedia

    INDEX
    Explanations

    negation/doubt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PASS
    -0.06
    pts
    -0.06
    loyd
    -0.06
     Barnes
    -0.06
    osen
    -0.06
     百度收录
    -0.06
    绿
    -0.06
    奔
    -0.06
     ＼:
    -0.06
    DataSetChanged
    -0.06
    POSITIVE LOGITS
     فوت
    0.07
     mechan
    0.07
     potato
    0.06
    _pointer
    0.06
    .Data
    0.06
     Operational
    0.06
    �
    0.06
     relatively
    0.06
     feeder
    0.06
    �
    0.06
    Act Density 0.052%

    No Known Activations