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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Nitro
    0.45
     overhang
    0.44
     remote
    0.43
    🚀
    0.41
     rocket
    0.41
     nitro
    0.41
     direct
    0.40
     ceiling
    0.39
     desire
    0.39
     достат
    0.39
    POSITIVE LOGITS
     서로
    0.46
    myCollision
    0.45
     Църква
    0.44
    걔
    0.41
     евре
    0.40
    ฤษ
    0.39
    可能会
    0.39
     चूंकि
    0.39
     회사
    0.38
     фирмы
    0.38
    Act Density 0.009%

    No Known Activations