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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     protective
    1.19
    欉
    1.18
    śmy
    1.14
     friendship
    1.11
    毀
    1.10
    숍
    1.09
    広い
    1.09
     কলেজে
    1.09
     کم
    1.08
    hardening
    1.08
    POSITIVE LOGITS
    e
    1.43
    ו
    1.38
    u
    1.31
    pets
    1.24
     iPhones
    1.23
    i
    1.18
     pats
    1.18
    ا
    1.17
    th
    1.13
    يت
    1.11
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.