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

    Neuronpedia

    INDEX
    Explanations

    directory paths, web servers, data, var

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     स्त्रीलिंग
    0.41
    筷
    0.41
     creamy
    0.40
     methionine
    0.39
     ላ
    0.39
    ជ្រ
    0.39
     fuzzy
    0.38
    fetching
    0.38
     hazy
    0.37
    模糊
    0.37
    POSITIVE LOGITS
    data
    0.66
     DATA
    0.66
     data
    0.63
     Data
    0.63
    DATA
    0.61
     var
    0.60
    Data
    0.59
    var
    0.57
    数据
    0.55
    www
    0.54
    Act Density 0.017%

    No Known Activations