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

    Neuronpedia

    INDEX
    Explanations

    describing environments and aesthetics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ϕ
    1.17
    ündet
    1.10
    عى
    1.09
    այի
    1.05
    вости
    1.03
     Ν
    1.03
    ತ್ಮ
    1.02
     Terminator
    1.02
    <unused6>
    1.00
     закона
    0.99
    POSITIVE LOGITS
     spacious
    2.10
     amenities
    1.88
     luxurious
    1.82
     décor
    1.81
     renovated
    1.80
     beautiful
    1.80
     rooms
    1.78
     furnishings
    1.71
     bathrooms
    1.70
     Spacious
    1.70
    Act Density 0.104%

    No Known Activations