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

    Neuronpedia

    INDEX
    Explanations

    references to building structures and outdoor settings

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

    outdoor locations and exterior surfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     room
    -0.43
     floor
    -0.41
    didSet
    -0.40
     Room
    -0.36
     rooms
    -0.36
     Zeller
    -0.36
     vloer
    -0.35
    反
    -0.35
    gonic
    -0.34
     furnishing
    -0.34
    POSITIVE LOGITS
     outdoor
    0.65
     outdoors
    0.63
    rungsseite
    0.61
    Outdoor
    0.60
    outdoor
    0.60
     Outdoor
    0.57
     ogrod
    0.55
     yard
    0.52
    LLocation
    0.52
    Бахар
    0.50
    Act Density 0.097%

    No Known Activations