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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -story
    -0.07
    Pooling
    -0.07
     lenders
    -0.07
     موارد
    -0.07
    ्पष
    -0.07
     ремон
    -0.07
    нося
    -0.06
     lavender
    -0.06
    (rel
    -0.06
     monoc
    -0.06
    POSITIVE LOGITS
     Rick
    0.07
    Yang
    0.07
    zi
    0.07
     Toplam
    0.06
    _DO
    0.06
    ografia
    0.06
    (Common
    0.06
    DF
    0.06
     ****************
    0.06
     İnsan
    0.06
    Act Density 0.161%

    No Known Activations