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

    Neuronpedia

    INDEX
    Explanations

    Google Drive, Docs, Sheets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embroidered
    0.42
     ریا
    0.40
    셧
    0.40
     Embro
    0.39
    ()<<
    0.39
     mammal
    0.38
     mammalian
    0.38
     Mamm
    0.38
     acoust
    0.38
     silk
    0.38
    POSITIVE LOGITS
    Google
    0.85
     Google
    0.80
     Drive
    0.73
     Docs
    0.73
     Spreadsheet
    0.72
     Gmail
    0.70
     spreadsheet
    0.70
     Sheets
    0.70
    Drive
    0.69
    Sheets
    0.67
    Act Density 0.024%

    No Known Activations