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

    Neuronpedia

    INDEX
    Explanations

    scientific and academic societies and academies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NgramModel
    0.59
    <unused988>
    0.57
    ဋ
    0.57
    ‌‌
    0.56
    |।
    0.55
    <unused1011>
    0.55
    followlike
    0.54
     líderes
    0.52
    éfonos
    0.52
     dhinak
    0.52
    POSITIVE LOGITS
     Society
    0.78
     Societies
    0.75
    ↵↵
    0.72
     as
    0.65
    A
    0.63
    Lu
    0.62
    W
    0.62
    X
    0.62
    Society
    0.61
    Sci
    0.61
    Act Density 0.001%

    No Known Activations