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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    es
    0.99
    𝘀
    0.89
    نا
    0.84
    ی
    0.81
    ول
    0.80
    ين
    0.79
    ین
    0.78
    م
    0.78
    s
    0.77
    m
    0.75
    POSITIVE LOGITS
     неболь
    0.86
    ções
    0.86
     медве
    0.81
     chord
    0.80
     эта
    0.79
     orbital
    0.77
     debilit
    0.76
     não
    0.75
    ↵↵↵
    0.74
     powerful
    0.74
    Act Density 0.000%

    No Known Activations