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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     yattha
    0.46
     pavattati
    0.41
    ड़ब
    0.41
    ambilan
    0.40
     guiclass
    0.40
    线性
    0.40
     ettha
    0.39
    傆
    0.39
    жина
    0.39
    パック
    0.37
    POSITIVE LOGITS
    lust
    0.45
     Lust
    0.42
     concentrations
    0.41
     "<<
    0.39
     Clustering
    0.38
     lust
    0.37
    чами
    0.37
     моз
    0.37
    erase
    0.36
     Frost
    0.36
    Act Density 0.000%

    No Known Activations