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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     আকর্ষণ
    0.51
     приготов
    0.50
     delicioso
    0.50
     кожа
    0.49
     मरम्मत
    0.49
     ремонт
    0.48
     подойдет
    0.48
     увла
    0.48
     итальян
    0.48
     lotions
    0.47
    POSITIVE LOGITS
    >
    0.62
    0.62
    \
    0.59
    the
    0.57
            
    0.56
    x
    0.55
    ↵
    0.54
    s
    0.52
                
    0.52
    描述
    0.51
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.