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

    Neuronpedia

    INDEX
    Explanations

    count

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    只怕
    -0.08
     древ
    -0.07
     Travel
    -0.07
    سوف
    -0.07
    ڷ
    -0.07
    female
    -0.07
    肥胖
    -0.07
     bacterial
    -0.07
    的成长
    -0.06
    啵
    -0.06
    POSITIVE LOGITS
     المشروع
    0.07
     cass
    0.07
    ции
    0.07
     assertions
    0.07
    احتجاج
    0.07
    ﾖ
    0.07
    ([('
    0.07
    =>"
    0.06
    _pipeline
    0.06
    Making
    0.06
    Act Density 0.004%

    No Known Activations