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

    Neuronpedia

    INDEX
    Explanations

    URLs and web addresses

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

    URLs and web addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.68
    Portail
    -0.62
     autorytatywna
    -0.60
    parsedMessage
    -0.57
     jScrollPane
    -0.57
     MainAxisSize
    -0.56
     FetchType
    -0.55
     ویکی‌پدی
    -0.55
     lenker
    -0.54
    AddTagHelper
    -0.54
    POSITIVE LOGITS
    ://
    0.50
     the
    0.40
    しも
    0.39
    About
    0.37
     ditto
    0.36
     いち
    0.35
    дай
    0.35
     Hydro
    0.34
     Dune
    0.34
    )';
    0.34
    Act Density 0.031%

    No Known Activations