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

    Neuronpedia

    INDEX
    Explanations

    specific references to publication details or issue numbers in text

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

    issue numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.85
    queryInterface
    -0.77
    ValueStyle
    -0.76
    httphttps
    -0.75
    aarrggbb
    -0.75
     Chwiliwch
    -0.75
     BoxFit
    -0.70
     للمعارف
    -0.70
     AssemblyProduct
    -0.69
     ModelExpression
    -0.69
    POSITIVE LOGITS
     format
    0.40
     os
    0.39
    handler
    0.38
     Hand
    0.37
     si
    0.37
     Post
    0.36
     Boy
    0.35
     sel
    0.35
    ,
    0.35
     Format
    0.34
    Act Density 0.069%

    No Known Activations