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

    Neuronpedia

    INDEX
    Explanations

    terms related to storage furniture, specifically drawers and cabinets

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

    drawer, drawers, compartment, trays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    -0.48
    virt
    -0.48
    <u>
    -0.48
    specialchars
    -0.47
     Holy
    -0.45
    <i>
    -0.45
    s
    -0.44
     offend
    -0.44
     Brice
    -0.44
     Ne
    -0.44
    POSITIVE LOGITS
     drawer
    1.16
     Drawer
    1.09
     drawers
    1.02
    drawer
    0.92
    Drawer
    0.91
     tiroirs
    0.77
     gavetas
    0.66
    屉
    0.54
     cajones
    0.54
     dresser
    0.53
    Act Density 0.002%

    No Known Activations