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

    Neuronpedia

    INDEX
    Explanations

    religious buildings (mosques, temples, cathedrals)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ancient
    0.67
     Ancient
    0.65
    Ancient
    0.64
     tombs
    0.63
     ancients
    0.63
     древ
    0.58
    ancient
    0.58
     monuments
    0.58
     monastic
    0.56
     monk
    0.55
    POSITIVE LOGITS
     DQ
    0.39
    屋さん
    0.37
    ulated
    0.37
    motion
    0.36
    ogni
    0.36
     vej
    0.36
     propriet
    0.35
     مقامی
    0.35
     குழு
    0.35
     Agencia
    0.34
    Act Density 0.017%

    No Known Activations