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

    Neuronpedia

    INDEX
    Explanations

    fortifications and buildings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cantik
    0.77
     হোমিওপ্যাথি
    0.72
    ouette
    0.70
     poesía
    0.70
     Балт
    0.70
    ohner
    0.69
     вяза
    0.69
     łyż
    0.69
    嗳
    0.68
     হোমিওপ্যাথ
    0.68
    POSITIVE LOGITS
     fortress
    2.30
     castle
    2.20
     palace
    2.04
     temple
    1.99
     Fortress
    1.96
     palaces
    1.88
     castles
    1.87
     citadel
    1.84
     fortifications
    1.80
     temples
    1.77
    Act Density 0.371%

    No Known Activations