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

    Neuronpedia

    INDEX
    Explanations

    in or out of bed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ActionsCallback
    0.39
     শ্রবণ
    0.36
     narod
    0.35
     correr
    0.35
     quantidades
    0.35
     केसर
    0.35
     accrue
    0.34
    骅
    0.34
     கொள்ளுங்கள்
    0.34
    臍
    0.34
    POSITIVE LOGITS
     bed
    2.89
     beds
    2.59
     Bed
    2.19
     Beds
    2.14
    ベッド
    2.11
    Bed
    2.09
    bed
    2.08
     giường
    2.06
    beds
    2.03
    床
    2.03
    Act Density 0.014%

    No Known Activations