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

    Neuronpedia

    INDEX
    Explanations

    code imports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    İR
    -0.07
    .piece
    -0.06
    _DOMAIN
    -0.06
    親
    -0.06
    火
    -0.06
    NW
    -0.06
    tcp
    -0.06
     farming
    -0.06
    ocode
    -0.06
     beers
    -0.06
    POSITIVE LOGITS
    outlined
    0.07
     адміністратив
    0.06
    controlled
    0.06
     přízn
    0.06
    .Cons
    0.06
    しかし
    0.06
    ！');↵
    0.06
     chimpan
    0.06
     Sext
    0.06
     diaper
    0.06
    Act Density 0.021%

    No Known Activations