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

    Neuronpedia

    INDEX
    Explanations

    difficulty levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?!"
    0.41
     kilograms
    0.38
    titulo
    0.38
    ваете
    0.38
    !");
    0.37
    与此同时
    0.37
    !";
    0.37
    ৈধ
    0.37
    !",
    0.36
    !!!"
    0.36
    POSITIVE LOGITS
     moderately
    0.47
     متوسط
    0.41
     Occasionally
    0.40
     בעי
    0.38
     مدى
    0.36
     למ
    0.36
     ले
    0.36
     خاصة
    0.36
     insbesondere
    0.36
     বিশেষ
    0.36
    Act Density 0.014%

    No Known Activations