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

    Neuronpedia

    INDEX
    Explanations

    tests/trials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peint
    -0.08
     arg
    -0.08
    ترنت
    -0.07
    ాతో
    -0.07
    Anth
    -0.07
     complications
    -0.07
    రు
    -0.07
     Vincent
    -0.07
    Rom
    -0.07
    _FROM
    -0.07
    POSITIVE LOGITS
     coba
    0.10
     tester
    0.09
    測
    0.09
     ಪರೀಕ್ಷ
    0.09
     পরীক্ষা
    0.09
    imonials
    0.09
     테스트
    0.08
     patience
    0.08
    测试
    0.08
    osterone
    0.08
    Act Density 0.032%

    No Known Activations