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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ñĩки
    -0.30
    hood
    -0.29
     nich
    -0.27
    anks
    -0.26
    æ¯ĶåĪĨ
    -0.26
    inox
    -0.26
    士
    -0.25
    itsu
    -0.25
    ç¥ŀè¯Ŀ
    -0.25
     fus
    -0.24
    POSITIVE LOGITS
    è¨Ģãģ£ãģŁ
    0.26
    tere
    0.26
     пен
    0.26
     Bett
    0.26
    éłĵ
    0.25
    WithPath
    0.25
    Await
    0.25
     Affero
    0.24
    æ·±åĪĩ
    0.24
    æĪĸèĢħåħ¶ä»ĸ
    0.24
    Act Density 0.006%

    No Known Activations

    This feature has no known activations.