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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ла
    2.61
    ק
    2.17
    า
    2.00
    ர்
    1.96
    ور
    1.91
    ת
    1.89
    ৪
    1.84
    ك
    1.84
    ार
    1.82
     таки
    1.81
    POSITIVE LOGITS
    Incoming
    1.73
    o
    1.73
     allgemein
    1.70
    ్‌
    1.70
    cluding
    1.65
    ுகிற
    1.61
    𝘢
    1.61
    序
    1.57
    িয়ে
    1.56
    नाल्ड
    1.56
    Act Density 0.282%

    No Known Activations