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

    Neuronpedia

    INDEX
    Explanations

    references to locations and directions within a domestic environment

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

    upstairs downstairs movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.67
    RenderAtEndOf
    -0.63
     esternos
    -0.63
     titolata
    -0.62
     zwiſchen
    -0.61
     ainfi
    -0.61
     queſta
    -0.61
     Infór
    -0.60
     gydy
    -0.60
     $_(
    -0.59
    POSITIVE LOGITS
     stairs
    0.54
     staircase
    0.53
     upstairs
    0.52
     downstairs
    0.51
     stair
    0.50
     Stair
    0.49
     bedroom
    0.49
    楼梯
    0.49
    Upstairs
    0.46
    Stair
    0.46
    Act Density 0.059%

    No Known Activations