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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     yapar
    0.43
     ребят
    0.42
    imizi
    0.42
    reven
    0.41
    seer
    0.40
    heaven
    0.40
    ten
    0.39
    duino
    0.39
    wonderful
    0.39
    ZER
    0.39
    POSITIVE LOGITS
    ↵
    0.54
     (
    0.38
     （
    0.34
    ：（
    0.32
     احتم
    0.31
     '/':
    0.29
     darunter
    0.29
    های
    0.28
     broader
    0.28
     notably
    0.28
    Act Density 0.000%

    No Known Activations