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

    Neuronpedia

    INDEX
    Explanations

    orienteering and cross-country

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    只为
    -0.09
    sink
    -0.08
    named
    -0.07
    涎
    -0.07
    不是一个
    -0.07
    (WebDriver
    -0.07
    ⏶
    -0.07
     TensorFlow
    -0.07
    liğinde
    -0.07
    宽敞
    -0.07
    POSITIVE LOGITS
     oral
    0.07
    村
    0.07
     ports
    0.07
    <len
    0.07
    meta
    0.07
     처리
    0.06
     verdad
    0.06
    _Delete
    0.06
     دي
    0.06
    Github
    0.06
    Act Density 0.009%

    No Known Activations