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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    银行
    -0.07
    ='${
    -0.07
     PubMed
    -0.06
     Brace
    -0.06
     гра
    -0.06
     составляет
    -0.06
     نام
    -0.06
    府
    -0.06
    .Relative
    -0.06
     pistols
    -0.06
    POSITIVE LOGITS
    ทร
    0.06
    .mx
    0.06
     mechanism
    0.06
    оваться
    0.06
     Lưu
    0.06
     MacOS
    0.06
    entionPolicy
    0.06
    ічний
    0.06
     Search
    0.06
    Ware
    0.06
    Act Density 0.000%

    No Known Activations