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

    Neuronpedia

    INDEX
    Explanations

    interjections and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erequisite
    0.36
    iede
    0.35
    ()->
    0.34
     ಕಾರ
    0.33
     লেখকের
    0.33
    壞
    0.32
    Ř
    0.32
     ڈی
    0.32
     POSSIBILITY
    0.32
    DeleteDialogOpen
    0.32
    POSITIVE LOGITS
     huh
    1.07
    吧
    1.05
    ですね
    1.03
     eh
    0.97
     übrigens
    0.93
     imo
    0.92
     IMHO
    0.90
     BTW
    0.89
     nhé
    0.88
     btw
    0.88
    Act Density 0.172%

    No Known Activations