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

    Neuronpedia

    INDEX
    Explanations

    creating test examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     William
    0.44
     Christina
    0.42
     Santa
    0.42
     glowing
    0.40
     Glowing
    0.40
     Spr
    0.39
     Beth
    0.38
     Watt
    0.38
     Grit
    0.38
     River
    0.38
    POSITIVE LOGITS
     test
    0.78
    test
    0.77
    测试
    0.75
     тесто
    0.73
    Test
    0.69
    TEST
    0.69
     टेस्ट
    0.69
     테스트
    0.68
     টেস্ট
    0.63
    テスト
    0.61
    Act Density 0.164%

    No Known Activations