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

    Neuronpedia

    INDEX
    Explanations

    Enneagram personality types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    0.72
    ات
    0.70
     ו
    0.68
    <0x80>
    0.66
     و
    0.65
     с
    0.63
     ও
    0.63
     applicability
    0.63
     и
    0.61
     utterly
    0.61
    POSITIVE LOGITS
    toluene
    0.66
    뉜
    0.64
    ਨੀ
    0.61
    tfidf
    0.61
    familyName
    0.58
    toilet
    0.57
     Swezey
    0.57
     Colchester
    0.57
    쭤
    0.57
     सिसोदिया
    0.56
    Act Density 0.001%

    No Known Activations