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

    Neuronpedia

    INDEX
    Explanations

    document types and specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sombras
    0.30
     passage
    0.29
     सबक
    0.29
    zczeg
    0.29
     mesmo
    0.29
     Passage
    0.29
    ्ञ
    0.28
     mismo
    0.28
    <0xDE>
    0.28
    ﻐ
    0.28
    POSITIVE LOGITS
     পিডিএফ
    0.45
     pdf
    0.43
    pdf
    0.42
     पीडीएफ
    0.41
    docx
    0.40
    📄
    0.39
     Pdf
    0.39
    PDF
    0.38
     PDF
    0.38
     doesnt
    0.35
    Act Density 0.000%

    No Known Activations