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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.42
     metabolized
    0.41
     regimens
    0.41
    readers
    0.41
     mechanisms
    0.40
     colonized
    0.40
     novels
    0.40
     editorials
    0.39
    morrow
    0.39
     multitudes
    0.38
    POSITIVE LOGITS
     pokazuje
    0.44
    Concerning
    0.43
     مبنی
    0.43
    注意的是
    0.42
    zeigt
    0.42
    ಿಸಿದೆ
    0.42
     решила
    0.40
     Gọi
    0.40
     하다
    0.40
     Eğer
    0.39
    Act Density 0.260%

    No Known Activations