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

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prestige
    -0.09
    .Vertex
    -0.08
     Олим
    -0.08
     만든
    -0.08
     mim
    -0.08
    ้ม
    -0.08
     recre
    -0.08
     olímp
    -0.08
     Judges
    -0.08
     ях
    -0.08
    POSITIVE LOGITS
    .search
    0.15
     grep
    0.15
    検索
    0.15
     searching
    0.14
    搜索
    0.14
    (search
    0.14
     поиска
    0.14
    Searching
    0.13
    -search
    0.13
     Searching
    0.13
    Act Density 0.007%

    No Known Activations