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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     piens
    0.62
    पयोग
    0.60
     produzir
    0.59
    Ông
    0.59
    ⊢
    0.58
     它
    0.57
     weaning
    0.57
    ﻤ
    0.57
    含量
    0.57
    ﺐ
    0.56
    POSITIVE LOGITS
    ной
    0.66
    і
    0.65
     Р
    0.63
    ר
    0.62
     llevó
    0.60
     llevaron
    0.58
     fece
    0.58
    К
    0.57
     doppia
    0.57
     ר
    0.57
    Act Density 0.000%

    No Known Activations