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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     prefque
    0.66
     averiguar
    0.64
     школ
    0.61
     pedir
    0.60
     pensez
    0.60
     arquivos
    0.59
     automóviles
    0.59
     hogares
    0.59
     архіви
    0.59
     archivos
    0.58
    POSITIVE LOGITS
     That
    0.55
     ItemStack
    0.54
    ،
    0.52
     Disposal
    0.52
     the
    0.50
    স্ত
    0.50
    が
    0.50
    That
    0.49
    、
    0.49
     Empty
    0.49
    Act Density 0.000%

    No Known Activations