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

    Neuronpedia

    INDEX
    Explanations

    ocr/tesseract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    羯
    -0.07
     grazing
    -0.07
    otor
    -0.07
     Concurrent
    -0.07
    局副局长
    -0.07
     allergic
    -0.07
     forgiven
    -0.07
     };↵↵↵
    -0.07
     enjoy
    -0.06
    请点击
    -0.06
    POSITIVE LOGITS
    上司
    0.08
    ünkü
    0.07
     weakening
    0.07
     yük
    0.07
    :*
    0.07
    dığ
    0.06
    شرق
    0.06
    spi
    0.06
    ﲋ
    0.06
    祾
    0.06
    Act Density 0.000%

    No Known Activations