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

    Neuronpedia

    INDEX
    Explanations

    Supply and Demand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ban
    0.39
    を除
    0.37
    номо
    0.37
    で
    0.36
    arda
    0.36
     Hoa
    0.36
     Interests
    0.35
     Tant
    0.35
     Wart
    0.35
    Tür
    0.35
    POSITIVE LOGITS
    打包
    0.48
     }}=
    0.46
    🌒
    0.45
    🌭
    0.43
    🔦
    0.43
    😙
    0.42
     }=\
    0.41
    🔅
    0.41
     አስ
    0.41
    🧖
    0.41
    Act Density 0.000%

    No Known Activations