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

    Neuronpedia

    INDEX
    Explanations

    quotes and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dat
    -0.07
     itemView
    -0.07
     Đề
    -0.06
     สามารถ
    -0.06
    ционной
    -0.06
    jar
    -0.06
    _AspNet
    -0.06
     convertView
    -0.06
    远
    -0.06
     matchup
    -0.06
    POSITIVE LOGITS
    eous
    0.07
     Basic
    0.06
    leted
    0.06
    NH
    0.06
     ki
    0.06
    _HI
    0.06
    щий
    0.06
    щими
    0.06
    Library
    0.06
     volta
    0.06
    Act Density 0.088%

    No Known Activations