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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    新增
    -0.07
     gangs
    -0.07
     junk
    -0.07
    _NE
    -0.07
    ДЕ
    -0.06
     beaches
    -0.06
    ⴽ
    -0.06
    _results
    -0.06
    ,count
    -0.06
    白沙
    -0.06
    POSITIVE LOGITS
    😡
    0.07
    schlü
    0.07
    ListComponent
    0.07
    'à
    0.07
    ;element
    0.07
    ઽ
    0.07
    urga
    0.07
    Assembler
    0.07
     Dragons
    0.06
    躁
    0.06
    Act Density 0.006%

    No Known Activations