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

    Neuronpedia

    INDEX
    Explanations

    what if, what's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hvad
    0.43
    特点
    0.41
     виды
    0.41
     czym
    0.40
    哪些
    0.39
    អ្វី
    0.38
    通常の
    0.38
     கீழ்
    0.38
     तहत
    0.37
     অনুয
    0.37
    POSITIVE LOGITS
    soever
    0.55
     happened
    0.54
     Happened
    0.53
     if
    0.48
     ifs
    0.46
    ?!"
    0.44
    '
    0.43
    if
    0.43
    倘
    0.43
    hews
    0.42
    Act Density 0.013%

    No Known Activations