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

    Neuronpedia

    INDEX
    Explanations

    Subject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    势
    -0.09
    奇
    -0.08
    _PAR
    -0.08
    刑
    -0.07
     tough
    -0.07
     lacking
    -0.07
    -0.07
    理论
    -0.07
     absent
    -0.07
     Fantastic
    -0.07
    POSITIVE LOGITS
     Please
    0.09
     भेज
    0.09
     आले
    0.09
    Please
    0.09
     ગુજરાત
    0.09
     पंजाब
    0.09
     ایم
    0.09
     धन्यवाद
    0.09
     ارسال
    0.09
     sincere
    0.09
    Act Density 0.007%
    No Known Activations