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

    Neuronpedia

    INDEX
    Explanations

    references to social media and content creation

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

    share or comment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ailes
    -0.35
    d
    -0.31
    der
    -0.30
    周り
    -0.30
    memset
    -0.29
    舺
    -0.29
    tonode
    -0.29
    喻
    -0.28
    asai
    -0.28
     건
    -0.27
    POSITIVE LOGITS
    RegressionTest
    0.62
     للاسماء
    0.59
    DockStyle
    0.59
     disambiguazione
    0.55
     considérons
    0.55
    
    0.53
    Билгалдахарш
    0.52
    AddTagHelper
    0.52
    centralwidget
    0.52
     initComponents
    0.52
    Act Density 0.021%

    No Known Activations