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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     horseshoe
    0.46
     McEl
    0.43
     Form
    0.41
     außen
    0.39
    rendered
    0.38
    햇
    0.38
     آل
    0.38
    gus
    0.38
    Arr
    0.38
     Leit
    0.38
    POSITIVE LOGITS
     ду
    0.40
     судь
    0.38
     возрасте
    0.38
     sakte
    0.38
    僉
    0.37
    大き
    0.37
    ім
    0.36
     плохо
    0.36
     реа
    0.36
     প্রার্থীদের
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.