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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reduce
    -0.07
     people
    -0.07
    Many
    -0.07
    Al
    -0.06
    -budget
    -0.06
     //
↵
    -0.06
     chtěl
    -0.06
     scared
    -0.06
    Iterable
    -0.06
    };
    -0.06
    POSITIVE LOGITS
     Hòa
    0.07
     programm
    0.07
     sửa
    0.06
    .baidu
    0.06
     المنطقة
    0.06
     Rt
    0.06
     paras
    0.06
    升
    0.06
     Sour
    0.06
     Marcus
    0.06
    Act Density 0.006%

    No Known Activations