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

    Neuronpedia

    INDEX
    Explanations

    adult

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FromNib
    -0.07
    +↵↵
    -0.07
     intelig
    -0.07
    pong
    -0.07
     Selection
    -0.07
    Ⓨ
    -0.07
     إنه
    -0.07
    tréal
    -0.07
     slices
    -0.07
     GNOME
    -0.06
    POSITIVE LOGITS
     CharSet
    0.09
     advocated
    0.07
    (it
    0.07
     unlawful
    0.07
    嗤
    0.07
    弭
    0.07
    릳
    0.07
    wx
    0.07
    𫄷
    0.07
    剁
    0.07
    Act Density 0.007%

    No Known Activations