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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     polypropylene
    0.50
    Į
    0.47
    谎
    0.46
    Ĭ
    0.45
     Kiểm
    0.44
     Unless
    0.44
    ﻂ
    0.43
     ibuprofen
    0.43
    Кроме
    0.42
    핳
    0.42
    POSITIVE LOGITS
    oretical
    0.59
    theless
    0.56
    some
    0.56
    s
    0.55
    которые
    0.53
    empre
    0.53
    ant
    0.51
    eine
    0.50
    graduate
    0.50
    an
    0.49
    Act Density 3.095%

    No Known Activations