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

    Neuronpedia

    INDEX
    Explanations

    architectural design, plans, media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     architet
    0.51
     architect
    0.48
     architekt
    0.47
     arquitect
    0.45
     architects
    0.45
     arquitet
    0.44
    architect
    0.44
    Designer
    0.43
     충
    0.42
    建築
    0.41
    POSITIVE LOGITS
    NORM
    0.43
    seva
    0.41
    kách
    0.41
    éticas
    0.40
    राउंड
    0.39
     detalhes
    0.38
    恪
    0.38
    Eppo
    0.38
    تك
    0.38
    eworthy
    0.37
    Act Density 0.003%

    No Known Activations