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

    Neuronpedia

    INDEX
    Explanations

    personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ढ
    -0.06
    ทำงาน
    -0.06
     dagen
    -0.06
    rod
    -0.06
    Т
    -0.06
    iros
    -0.06
    Ger
    -0.06
     علت
    -0.06
    测试
    -0.06
    ('_
    -0.06
    POSITIVE LOGITS
    _$_
    0.07
    epar
    0.06
     fitte
    0.06
    ocial
    0.06
    _tC
    0.06
    >"↵
    0.06
     мик
    0.06
    寶
    0.06
     Thị
    0.06
    .managed
    0.06
    Act Density 0.067%

    No Known Activations