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

    Neuronpedia

    INDEX
    Explanations

    code/file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -wsj
    -0.07
    ently
    -0.07
    ALLY
    -0.07
    ikel
    -0.07
    الت
    -0.07
    精装
    -0.07
    琮
    -0.07
    特色社会
    -0.06
    .tagName
    -0.06
    icious
    -0.06
    POSITIVE LOGITS
    _dx
    0.08
     grat
    0.07
    邺
    0.07
    同時に
    0.07
     perpetrators
    0.07
     vb
    0.07
    utta
    0.07
    贯
    0.07
     Рус
    0.07
     Kunden
    0.07
    Act Density 0.002%

    No Known Activations