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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "up" in various contexts

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

    "Up"

    np_acts-logits-general · gemini-2.0-flash

    up until, up-close

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebServlet
    -0.77
    はじめに
    -0.77
    ]--;
    -0.73
     AssemblyCompany
    -0.73
     adel
    -0.71
    addCriterion
    -0.65
    ことができました
    -0.63
    Spoiler
    -0.62
    posób
    -0.60
    MemoryWarning
    -0.60
    POSITIVE LOGITS
     UP
    0.74
    upu
    0.65
    UP
    0.63
    ⤴
    0.63
     régulière
    0.62
     Up
    0.61
    WARDS
    0.60
    wards
    0.58
    ↑↑
    0.57
     up
    0.56
    Act Density 0.230%

    No Known Activations