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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     rodzin
    0.90
    ake
    0.87
    부터
    0.82
    ke
    0.82
     malo
    0.82
    Ole
    0.82
    tan
    0.81
    ilen
    0.80
    ten
    0.79
    0.79
    POSITIVE LOGITS
    ن
    0.96
    мә
    0.72
     circuito
    0.68
    δήποτε
    0.67
    пол
    0.65
    ابقات
    0.65
    édrale
    0.65
     топлива
    0.64
    贏
    0.64
    ↥
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.