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

    Neuronpedia

    INDEX
    Explanations

    key levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nos
    0.47
     dins
    0.40
     patt
    0.38
     lung
    0.38
     trate
    0.38
     مدار
    0.37
     praises
    0.36
    iral
    0.36
     luj
    0.36
    mt
    0.36
    POSITIVE LOGITS
     ઝડ
    0.45
    本書
    0.44
     क्लो
    0.43
     bookstore
    0.43
     Indianapolis
    0.42
     फिटनेस
    0.42
     Букмекер
    0.41
    本书
    0.41
     কোনটি
    0.41
     পুস্তকের
    0.40
    Act Density 0.000%

    No Known Activations