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

    Neuronpedia

    INDEX
    Explanations

    references to underground structures and shelters

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

    Interiors, navigation, or systems

    np_acts-logits-general · gemini-2.0-flash

    interior spaces and rooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     roadside
    -0.67
     ostavi
    -0.58
     متعلقه
    -0.56
     landowner
    -0.55
     depositphotos
    -0.54
     dorp
    -0.54
    inka
    -0.54
     uplands
    -0.54
    iecie
    -0.53
    PreferredItem
    -0.53
    POSITIVE LOGITS
     inside
    0.86
     interior
    0.85
     floor
    0.85
     intérieur
    0.85
     rooms
    0.83
     ceiling
    0.82
     ceilings
    0.80
     hallway
    0.79
     Inside
    0.79
     walls
    0.78
    Act Density 0.317%

    No Known Activations