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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Adik
    1.07
     አይደ
    1.05
    dz
    1.05
    ංශ
    1.04
     navbar
    1.04
    统治
    1.02
    swering
    1.02
    गोलिक
    1.00
    ｂ
    1.00
    कुर
    0.99
    POSITIVE LOGITS
    ા
    1.15
     refe
    1.03
    o
    0.97
    க்காக
    0.96
    反対
    0.93
    テー
    0.92
     wildfires
    0.92
    主席
    0.92
    เน
    0.92
    ه
    0.91
    Act Density 0.000%

    No Known Activations