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

    Neuronpedia

    INDEX
    Explanations

    names, naming,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这是
    0.68
    這是
    0.64
     барои
    0.64
     这是
    0.64
     delineation
    0.63
    这是一个
    0.61
     изменение
    0.59
     განს
    0.59
    ালোচনা
    0.57
     بخشی
    0.57
    POSITIVE LOGITS
     bernama
    0.73
    名叫
    0.70
     named
    0.69
     other
    0.63
     namesake
    0.62
     namens
    0.62
     famous
    0.61
     titular
    0.61
     eponymous
    0.61
     listed
    0.60
    Act Density 0.233%

    No Known Activations