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

    Neuronpedia

    INDEX
    Explanations

    date formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     senyawa
    0.43
     φυ
    0.39
    对象的
    0.39
     anisotrop
    0.37
     cellulosic
    0.36
     ordinairement
    0.36
     chitosan
    0.36
     persyaratan
    0.36
     trypt
    0.36
     ciri
    0.35
    POSITIVE LOGITS
     Parece
    0.39
    네요
    0.37
     haven
    0.36
     disappointing
    0.36
     hasn
    0.36
    了一些
    0.35
     बिता
    0.35
     હતો
    0.35
     منذ
    0.34
    راءة
    0.34
    Act Density 0.082%

    No Known Activations