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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ج
    0.69
     quasip
    0.66
    чис
    0.66
    لى
    0.65
    אות
    0.65
     проє
    0.64
    鞆
    0.64
    尽管
    0.64
    ं
    0.64
    ہ
    0.64
    POSITIVE LOGITS
    ul
    1.08
     только
    1.02
     tomar
    1.02
     itens
    1.00
     añadir
    0.98
    s
    0.98
     nenhum
    0.96
    ka
    0.95
     который
    0.95
     líquidos
    0.95
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.