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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     célula
    1.05
     permitirá
    1.00
     ornamentation
    0.97
     resuelve
    0.96
     atividade
    0.95
     liberdade
    0.95
     aplicativo
    0.92
     divertido
    0.89
     ouvir
    0.89
     aplicando
    0.88
    POSITIVE LOGITS
    מ
    0.85
    其
    0.83
    aris
    0.83
    ני
    0.81
    خ
    0.81
    新
    0.78
    後
    0.76
    מי
    0.76
    后
    0.76
    少
    0.75
    Act Density 0.000%

    No Known Activations