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

    Neuronpedia

    INDEX
    Explanations

    of by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     narrator
    -0.07
    以上
    -0.07
    岁
    -0.07
     نيز
    -0.07
     either
    -0.06
     Yep
    -0.06
     tb
    -0.06
    يه
    -0.06
    ognition
    -0.06
    testimonial
    -0.06
    POSITIVE LOGITS
     Gov
    0.07
     прим
    0.06
    _$_
    0.06
    �
    0.06
     obst
    0.06
     suburban
    0.06
    -Mail
    0.06
     thị
    0.06
    !!!↵↵
    0.06
    -sem
    0.06
    Act Density 0.028%

    No Known Activations