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

    Neuronpedia

    INDEX
    Explanations

    words ending in in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يون
    0.44
    .??.??"]
    0.42
    inplace
    0.39
     !")
    0.39
    =="
    0.39
    iunea
    0.39
    ^{*},
    0.38
    迩
    0.38
     SizedBox
    0.38
    ிருப்ப
    0.38
    POSITIVE LOGITS
    ning
    0.62
    ny
    0.61
    ners
    0.58
    ormal
    0.55
    ator
    0.53
    novation
    0.51
    strument
    0.51
    netje
    0.51
    ette
    0.50
    nesota
    0.50
    Act Density 0.056%

    No Known Activations