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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    表态
    -0.08
     mamma
    -0.07
     profesional
    -0.07
    _setting
    -0.07
    ياه
    -0.07
    ARGE
    -0.07
    _write
    -0.07
    访问
    -0.07
     Submission
    -0.07
    _call
    -0.07
    POSITIVE LOGITS
     EZ
    0.07
     pi
    0.07
    0.07
    歧
    0.07
     sab
    0.07
    不可或
    0.07
    火车
    0.06
    Ɛ
    0.06
     invisible
    0.06
    _In
    0.06
    Act Density 0.003%

    No Known Activations