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

    Neuronpedia

    INDEX
    Explanations

    descriptions of residential properties and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding numbers before "bedroom" or "bathroom"

    np_acts-logits-general · gemini-2.0-flash

    numbers of bedrooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rhin
    -0.45
    ولت
    -0.44
    тана
    -0.44
     teil
    -0.43
     Ache
    -0.42
     égard
    -0.42
     Alloy
    -0.42
    nisses
    -0.42
     Sache
    -0.41
     &___
    -0.41
    POSITIVE LOGITS
     master
    1.02
     bedrooms
    0.97
    master
    0.86
     Master
    0.85
    Master
    0.84
    Bedrooms
    0.82
    MASTER
    0.82
     bedroom
    0.80
     MASTER
    0.79
     Bedrooms
    0.73
    Act Density 0.040%

    No Known Activations