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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     яй
    0.47
     влас
    0.45
     thisobject
    0.44
    ϙ
    0.44
    🇶
    0.44
    кт
    0.44
     பார்க்கலாம்
    0.43
     ಪ್ರಮಾಣ
    0.43
     chuẩn
    0.43
     поведения
    0.43
    POSITIVE LOGITS
     Moulin
    0.55
     \
    0.54
     tiny
    0.48
     Leuven
    0.48
     Damascus
    0.48
     lou
    0.47
    큰
    0.47
    ميم
    0.47
    se
    0.46
    ke
    0.46
    Act Density 0.001%

    No Known Activations