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

    Neuronpedia

    INDEX
    Explanations

    Repetition and alliteration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fy
    -0.08
    /.↵
    -0.07
     Essays
    -0.07
     Pis
    -0.07
     filling
    -0.07
     fillings
    -0.07
    Fy
    -0.07
     poeta
    -0.07
     Pisa
    -0.07
     Fy
    -0.06
    POSITIVE LOGITS
     તૈય
    0.09
     เช่น
    0.09
     eigener
    0.08
     إطلاق
    0.08
     شرایط
    0.08
     ծ
    0.08
     همان
    0.08
     ����
    0.08
    გან
    0.08
     irresponsible
    0.08
    Act Density 0.002%

    No Known Activations