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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     После
    0.69
    लेकिन
    0.65
    उनके
    0.65
     attano
    0.63
     查看
    0.63
     प्रवीण
    0.63
    䀓
    0.63
    ਸ
    0.62
     उनकी
    0.61
    मुख्यमंत्री
    0.61
    POSITIVE LOGITS
     in
    0.71
     of
    0.65
     auf
    0.61
    の
    0.59
     on
    0.57
     aus
    0.55
     по
    0.52
     affine
    0.52
     akan
    0.51
    ̀
    0.51
    Act Density 0.001%

    No Known Activations