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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    لیکن
    0.49
    ทั้งหมด
    0.47
     tidak
    0.43
    但不
    0.42
    нче
    0.40
     modern
    0.39
     no
    0.39
     современного
    0.39
    modern
    0.38
     moderno
    0.38
    POSITIVE LOGITS
    আগ
    0.48
     climates
    0.47
     인
    0.46
     while
    0.46
     estrateg
    0.45
    ⼈
    0.45
     pamię
    0.44
    คลิ
    0.43
     entitles
    0.43
     onClick
    0.42
    Act Density 0.009%

    No Known Activations