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

    Neuronpedia

    INDEX
    Explanations

    adverbs describing actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Genre
    -0.27
    ãģ«æĪ»
    -0.26
    baum
    -0.26
    chemy
    -0.26
    é¹ĺ
    -0.25
    ãģ¨ãģ«ãģĭãģı
    -0.25
    çĹĺ
    -0.25
     Tart
    -0.24
    æŃ»åİ»
    -0.24
     reverted
    -0.23
    POSITIVE LOGITS
    edBy
    0.28
     delights
    0.26
    ç½®
    0.26
    ilm
    0.26
    antly
    0.25
    cue
    0.25
    FullYear
    0.25
    åħ¥åѦ
    0.25
     maxim
    0.25
    oref
    0.25
    Act Density 0.018%

    No Known Activations