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

    Neuronpedia

    INDEX
    Explanations

    mainstream/mainland

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mainstream
    -1.66
     craft
    -0.94
     minimizar
    -0.92
     traditionnels
    -0.85
     ligiloj
    -0.85
     fallu
    -0.84
    主流
    -0.83
     pulito
    -0.81
     minimize
    -0.80
     Craft
    -0.80
    POSITIVE LOGITS
    s
    0.85
    ers
    0.65
    ی
    0.61
    sing
    0.57
    ים
    0.56
    WireFormat
    0.54
    ся
    0.53
    ies
    0.52
    scot
    0.51
    sver
    0.51
    Act Density 0.377%

    No Known Activations