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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences and list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    δε
    0.47
    딨
    0.38
     মনোভাব
    0.38
    Default
    0.37
    ʡ
    0.37
    zilla
    0.37
    是你
    0.37
    ेंटिस
    0.37
    াহিয়া
    0.36
     blames
    0.36
    POSITIVE LOGITS
    2
    0.55
     giugno
    0.52
    3
    0.50
    0
    0.50
     consecutive
    0.50
     CHAPTER
    0.49
     연속
    0.48
    -
    0.47
     Ways
    0.47
    1
    0.47
    Act Density 0.021%

    No Known Activations