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

    Neuronpedia

    INDEX
    Explanations

    technical requirements and needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \}=\
    1.17
    :\\
    1.08
     cosidd
    1.02
    utils
    1.00
    人们
    0.99
    -\\
    0.99
     proverbial
    0.98
    <unused2121>
    0.97
    ಲಿಯ
    0.97
     internalized
    0.96
    POSITIVE LOGITS
     and
    1.09
     وت
    1.06
    ว้
    0.98
     וש
    0.93
     وتح
    0.93
    🌵
    0.90
     וב
    0.90
     тощо
    0.89
     etc
    0.88
    ׳
    0.86
    Act Density 0.170%

    No Known Activations