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

    Neuronpedia

    INDEX
    Explanations

    Code/logic representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indist
    -0.08
     febru
    -0.08
     intersections
    -0.08
    ிகழ
    -0.07
     {{↵
    -0.07
     مب
    -0.07
     occur
    -0.07
     male
    -0.07
    uellement
    -0.07
     pronounce
    -0.07
    POSITIVE LOGITS
    ayload
    0.09
    lar
    0.08
     책임
    0.08
    aryawan
    0.08
    责任
    0.08
     세계
    0.07
    ుల్
    0.07
    allery
    0.07
     Panda
    0.07
     世界
    0.07
    Act Density 0.000%

    No Known Activations