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

    Neuronpedia

    INDEX
    Explanations

    publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生于
    -0.07
     Bened
    -0.06
    是一种
    -0.06
     derives
    -0.06
    ểu
    -0.06
    了起来
    -0.06
    keyCode
    -0.06
     ngu
    -0.06
    来历
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Smart
    0.07
     Potato
    0.07
    .lock
    0.07
     Watch
    0.07
     Eaton
    0.07
    _objects
    0.07
    _SORT
    0.07
    螟
    0.07
    irtual
    0.07
    _msgs
    0.06
    Act Density 0.006%

    No Known Activations