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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     costly
    -0.07
    _RATE
    -0.07
     Virt
    -0.07
    -opt
    -0.07
     Red
    -0.07
    SRC
    -0.07
    加盟
    -0.07
     imperative
    -0.06
    ingular
    -0.06
     yii
    -0.06
    POSITIVE LOGITS
    东莞
    0.07
     jesteśmy
    0.07
    ഹ
    0.06
    واشن
    0.06
    ᕑ
    0.06
    �
    0.06
     Erdoğan
    0.06
     Glasses
    0.06
    tworzyć
    0.06
     Proposal
    0.06
    Act Density 0.001%

    No Known Activations