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

    Neuronpedia

    INDEX
    Explanations

    buildings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اؤن
    0.42
    atasi
    0.39
    ة
    0.39
    ussels
    0.39
    віч
    0.37
     खाते
    0.36
    ugd
    0.35
    oneph
    0.35
    beyond
    0.35
    ieb
    0.34
    POSITIVE LOGITS
     здание
    0.48
     buildings
    0.43
     edificio
    0.40
    Buildings
    0.40
     건물
    0.40
    멩
    0.40
     house
    0.39
     edifici
    0.39
     submit
    0.38
    𝙳
    0.38
    Act Density 0.002%

    No Known Activations