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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    най
    1.09
    க்கு
    1.08
     рост
    1.06
    ο
    1.06
    ;
    1.03
     kou
    1.01
     kary
    1.00
     litigation
    0.99
     inductor
    0.99
    col
    0.99
    POSITIVE LOGITS
    ع
    1.28
     fantastical
    1.28
    crafted
    1.26
    arrière
    1.25
    ەیە
    1.23
    ت
    1.22
    عرف
    1.21
    ރ
    1.18
    ᆭ
    1.17
    ச
    1.16
    Act Density 0.000%

    No Known Activations