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

    Neuronpedia

    INDEX
    Explanations

    news/politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.69
     Púb
    -0.68
    iasaan
    -0.66
     Económica
    -0.64
    pumpe
    -0.63
    ÚBL
    -0.62
    CppMethod
    -0.62
     AppColors
    -0.61
    uyện
    -0.61
    Referees
    -0.61
    POSITIVE LOGITS
    right
    0.49
    цездатний
    0.45
    MessageTagHelper
    0.45
    net
    0.43
    EDEFAULT
    0.42
     transfieras
    0.42
    JspWriter
    0.41
    कृत
    0.41
     Euro
    0.40
    niająca
    0.40
    Act Density 0.008%

    No Known Activations