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

    Neuronpedia

    INDEX
    Explanations

    comparative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ens
    -0.07
    _Instance
    -0.07
    /sdk
    -0.06
    .SQLite
    -0.06
    不能再
    -0.06
    .Organization
    -0.06
    xFFFFFFFF
    -0.06
     attribution
    -0.06
    =""/>↵
    -0.06
     singapore
    -0.06
    POSITIVE LOGITS
    荒
    0.07
     küçük
    0.07
     tex
    0.07
     Tây
    0.07
     роль
    0.07
    Women
    0.07
     חמ
    0.07
     conteúdo
    0.07
    -archive
    0.06
     dort
    0.06
    Act Density 0.057%

    No Known Activations