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

    Neuronpedia

    INDEX
    Explanations

    part

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     свидетель
    -0.06
     zastup
    -0.06
    添加
    -0.06
     организации
    -0.06
    azi
    -0.06
    具
    -0.06
    ๊ก
    -0.06
     степени
    -0.06
     являются
    -0.06
    pageNum
    -0.06
    POSITIVE LOGITS
    貨
    0.07
     Н
    0.07
     Cultural
    0.06
    ragon
    0.06
    Revision
    0.06
    ozilla
    0.06
    ricula
    0.06
    .REACT
    0.06
     Revision
    0.06
     Catch
    0.06
    Act Density 0.020%

    No Known Activations