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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical methods and estimation techniques

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

    German "Sie" and Japanese "彼女"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.65
    XmlAccessType
    -0.63
    setVerticalGroup
    -0.63
    hyrchwyd
    -0.61
    ContentAsync
    -0.61
     المعيارى
    -0.58
    setHorizontal
    -0.58
     चीज़ों
    -0.58
     Pritchard
    -0.57
    TagMode
    -0.57
    POSITIVE LOGITS
     Sie
    1.66
    Sie
    1.52
     SIE
    0.90
     sie
    0.75
    SIE
    0.62
     sieve
    0.62
     Ihre
    0.61
     Ihnen
    0.59
     Siegel
    0.55
    You
    0.54
    Act Density 0.002%

    No Known Activations