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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    崎
    -0.07
     �
    -0.07
     weren
    -0.07
     �
    -0.07
    clip
    -0.07
    ﮀ
    -0.06
    户籍
    -0.06
     tüm
    -0.06
    acion
    -0.06
    emp
    -0.06
    POSITIVE LOGITS
    国会
    0.08
     RH
    0.08
     Sah
    0.07
    극
    0.07
     Slot
    0.07
     Injection
    0.07
     Pot
    0.07
     chambers
    0.07
     Ш
    0.07
     המשפט
    0.07
    Act Density 0.006%

    No Known Activations