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

    Neuronpedia

    INDEX
    Explanations

    programming errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cran
    -0.07
    lef
    -0.07
     nar
    -0.07
     Autos
    -0.06
     上
    -0.06
    在外
    -0.06
    Short
    -0.06
    富力
    -0.06
    larg
    -0.06
     fu
    -0.06
    POSITIVE LOGITS
    צטרף
    0.07
    뿅
    0.07
     Shia
    0.07
     promin
    0.07
     replied
    0.07
     ////
    0.07
     insist
    0.07
     يتعلق
    0.07
    مشار
    0.07
     dividends
    0.07
    Act Density 0.099%

    No Known Activations