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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     narrows
    0.83
     may
    0.78
     might
    0.77
    uf
    0.72
     stained
    0.68
    滤波器
    0.68
    ارب
    0.68
    ánchez
    0.67
     siblings
    0.67
     staining
    0.67
    POSITIVE LOGITS
    授权
    0.86
     कटोच
    0.64
    ٧
    0.62
    授
    0.62
    巌
    0.62
     निर्वा
    0.61
    juan
    0.61
     クロ
    0.61
     Tong
    0.60
     Seong
    0.60
    Act Density 0.000%

    No Known Activations