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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     těch
    0.58
     bekannten
    0.58
    itektur
    0.56
     تھی
    0.55
    LLCATS
    0.54
     聞い
    0.54
    arakatuh
    0.53
     ወቅ
    0.53
     खतरनाक
    0.52
    itherto
    0.52
    POSITIVE LOGITS
    t
    0.88
     for
    0.73
    ing
    0.66
    p
    0.64
     of
    0.60
    en
    0.59
    on
    0.58
    an
    0.56
    the
    0.55
     the
    0.54
    Act Density 0.001%

    No Known Activations