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

    Neuronpedia

    INDEX
    Explanations

    interior architectural spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     worthless
    0.43
     incriminating
    0.41
    Ny
    0.38
     misled
    0.38
    aság
    0.38
    ཨ
    0.38
     malicious
    0.38
     worsened
    0.38
     worsens
    0.38
    描写
    0.38
    POSITIVE LOGITS
     Architectural
    0.93
     sculptural
    0.87
     architectural
    0.86
     Revit
    0.85
     typology
    0.84
     facades
    0.77
     spaces
    0.75
     Spaces
    0.75
     amenity
    0.74
     materiality
    0.73
    Act Density 0.031%

    No Known Activations