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

    Neuronpedia

    INDEX
    Explanations

    screen density and image sizes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ihre
    -0.08
     По
    -0.07
     mannen
    -0.07
    Doctor
    -0.07
     estos
    -0.07
     thịt
    -0.07
    	tests
    -0.07
     boxer
    -0.06
    $h
    -0.06
    Cut
    -0.06
    POSITIVE LOGITS
    Americ
    0.07
    Attendance
    0.07
    ใหญ
    0.07
     Roch
    0.07
    Refer
    0.07
    attendance
    0.07
    .failed
    0.07
     Carousel
    0.07
    青睐
    0.06
    _US
    0.06
    Act Density 0.008%

    No Known Activations