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

    Neuronpedia

    INDEX
    Explanations

    This or only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Polaribacter
    0.52
     ಹೇಳಿದರು
    0.45
    ierten
    0.44
    ersen
    0.43
    뀔
    0.41
     Leur
    0.40
    zok
    0.40
     anisot
    0.40
    esine
    0.39
     ತೋರಿಸ
    0.39
    POSITIVE LOGITS
    ม่า
    0.48
     Đây
    0.47
     فقط
    0.47
     শুধু
    0.43
     chỉ
    0.43
     This
    0.42
     फक्त
    0.41
    শুধু
    0.41
     जितनी
    0.40
     Identifying
    0.40
    Act Density 0.001%

    No Known Activations