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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     seems
    0.48
    ر
    0.48
    ijnen
    0.46
     Still
    0.45
     Ald
    0.44
     bowling
    0.43
     still
    0.43
     Abhäng
    0.43
     Africa
    0.42
     while
    0.42
    POSITIVE LOGITS
     வால்
    0.49
     деше
    0.45
    ⒋
    0.44
    ᴦ
    0.44
     conclusión
    0.44
     мы
    0.43
     сало
    0.43
     советы
    0.43
    最終
    0.42
     площадь
    0.42
    Act Density 0.005%

    No Known Activations