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

    Neuronpedia

    INDEX
    Explanations

    (non-English) words or translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ross
    0.39
     গন্ধ
    0.39
     busy
    0.39
    cyclic
    0.39
     adding
    0.38
     aggi
    0.38
     ajout
    0.38
    Busy
    0.38
    ecycle
    0.38
     adds
    0.37
    POSITIVE LOGITS
     येथे
    0.50
     translated
    0.49
    translated
    0.46
     Translated
    0.44
     myBuilder
    0.43
     ترجم
    0.43
     Здесь
    0.42
     صفحات
    0.41
    在這裡
    0.40
     здесь
    0.39
    Act Density 0.001%

    No Known Activations