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

    Neuronpedia

    INDEX
    Explanations

    content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aange
    0.36
     ornith
    0.35
     eficaz
    0.35
     buildings
    0.34
     Indra
    0.34
    Nú
    0.34
    حاء
    0.34
     fick
    0.33
    Dib
    0.33
    Dam
    0.33
    POSITIVE LOGITS
     콘텐츠
    0.52
     уравнение
    0.49
    content
    0.48
     المعادله
    0.47
     कंटेंट
    0.46
    getCQL
    0.44
     content
    0.43
    コンテンツ
    0.43
     Content
    0.43
     CONTENT
    0.43
    Act Density 0.000%

    No Known Activations