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

    Neuronpedia

    INDEX
    Explanations

    features of a building layout

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

    directions and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.60
    istar
    -0.56
    canestro
    -0.54
    iocene
    -0.50
    TypedDataSet
    -0.49
     Савезне
    -0.49
    setVerticalGroup
    -0.48
    essment
    -0.48
     мәкал
    -0.47
    lanta
    -0.47
    POSITIVE LOGITS
    CloseOperation
    0.47
    tagHelperRunner
    0.43
     rooms
    0.37
     ouest
    0.36
     hallway
    0.36
     defaultstate
    0.36
     kitchen
    0.35
     room
    0.34
     corner
    0.32
    UpInside
    0.32
    Act Density 0.003%

    No Known Activations