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

    Neuronpedia

    INDEX
    Explanations

    dates, emails, file names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abelian
    0.48
    newspaper
    0.45
     unitarity
    0.44
    рованию
    0.44
     uart
    0.43
    KeyboardView
    0.41
     robbed
    0.41
     Klan
    0.40
    instagram
    0.40
    pthread
    0.40
    POSITIVE LOGITS
     PowerPoint
    0.45
     American
    0.41
     MOVE
    0.39
     передви
    0.38
     excel
    0.38
    移動
    0.38
     이동
    0.38
    Outlook
    0.38
     Outlook
    0.38
    outlook
    0.38
    Act Density 0.000%

    No Known Activations