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

    Neuronpedia

    INDEX
    Explanations

    references to paper and paper products

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

    "Paper" followed by a word describing its form/shape

    np_acts-logits-general · gemini-2.0-flash

    paper towel or PaperThin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.68
    Tikang
    -0.65
    AccessorTable
    -0.56
    Tiet
    -0.55
     typelib
    -0.50
    InSection
    -0.49
    migrationBuilder
    -0.49
    URLConnection
    -0.49
     religieuses
    -0.49
    createClass
    -0.47
    POSITIVE LOGITS
    clip
    0.88
    clips
    0.86
     towels
    0.77
     mache
    0.76
     Towel
    0.76
     towel
    0.75
    backs
    0.69
     mâ
    0.68
    mache
    0.67
    doll
    0.63
    Act Density 0.096%

    No Known Activations