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

    Neuronpedia

    INDEX
    Explanations

    word pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.50
     apl
    0.39
    ya
    0.35
     এবং
    0.35
     medical
    0.35
    ’,
    0.35
     or
    0.34
    science
    0.34
    为什么
    0.34
     and
    0.34
    POSITIVE LOGITS
    这份
    0.42
     זו
    0.40
    无疑
    0.38
     الحصه
    0.38
    ນີ້
    0.37
     NDVI
    0.37
     този
    0.37
    存档备份
    0.36
     เป็น
    0.36
    ckså
    0.35
    Act Density 0.016%

    No Known Activations