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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     רבות
    -0.07
    回到家
    -0.07
     Defendant
    -0.07
    =============↵
    -0.07
     sont
    -0.07
    ضرب
    -0.07
     genesis
    -0.06
     형
    -0.06
     negligence
    -0.06
     científ
    -0.06
    POSITIVE LOGITS
    卑
    0.08
    غان
    0.07
    _shared
    0.07
     MW
    0.07
     petty
    0.06
    omid
    0.06
    洌
    0.06
    ModelCreating
    0.06
     Bowling
    0.06
    商品房
    0.06
    Act Density 0.329%

    No Known Activations