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

    Neuronpedia

    INDEX
    Explanations

    damn, fucking, bloody, what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     為
    0.77
     želite
    0.75
    粨
    0.72
    ToSort
    0.71
    您的
    0.71
    fullName
    0.71
    Touches
    0.70
     कमजोरी
    0.70
     \&
    0.70
    ",&
    0.69
    POSITIVE LOGITS
     damn
    3.35
     fucking
    3.23
     damned
    3.05
     freaking
    2.81
    damn
    2.78
     bloody
    2.72
     darn
    2.65
     Damn
    2.62
     god
    2.42
     fuck
    2.41
    Act Density 0.161%

    No Known Activations