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

    Neuronpedia

    INDEX
    Explanations

    input/output examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पंडित
    0.74
    oyl
    0.62
    ardon
    0.62
     Fontaine
    0.61
    숟
    0.60
    conference
    0.60
     Gallup
    0.58
     Lyric
    0.58
     conference
    0.58
    اعر
    0.57
    POSITIVE LOGITS
    测试
    2.98
     tests
    2.97
     testing
    2.96
     test
    2.91
     Testing
    2.91
    Testing
    2.88
    測試
    2.75
     Tests
    2.73
     测试
    2.69
    Test
    2.69
    Act Density 0.385%

    No Known Activations