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

    Neuronpedia

    INDEX
    Explanations

    De

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rumors
    -0.06
    ��
    -0.06
     resembl
    -0.06
     insure
    -0.06
    ácil
    -0.06
    Even
    -0.06
     reli
    -0.06
     drunk
    -0.06
     bathrooms
    -0.06
    verages
    -0.06
    POSITIVE LOGITS
    _templates
    0.06
    leetcode
    0.06
     parç
    0.06
    (types
    0.06
     profesyonel
    0.06
     glaring
    0.06
     authentication
    0.06
     самостоятель
    0.06
     İmpar
    0.06
     bibli
    0.06
    Act Density 0.166%

    No Known Activations