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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    迷你
    0.65
    wür
    0.63
     cubs
    0.63
     Wür
    0.62
    icale
    0.60
     লেন
    0.60
    >→</
    0.60
     Fools
    0.60
    atche
    0.59
    estial
    0.58
    POSITIVE LOGITS
    EI
    0.52
     પહેલા
    0.51
    <unused539>
    0.51
    Adjacent
    0.50
     Efficiency
    0.50
     பாதுகா
    0.50
     ευ
    0.49
    ogenicity
    0.49
     బోర్
    0.49
     パ
    0.48
    Act Density 0.202%

    No Known Activations