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

    Neuronpedia

    INDEX
    Explanations

    entities, terms, or variables frequently associated with specific domains like medicine, mathematics, and programming

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

    Appears before or after uncommon words or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    checkerboard, content types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.80
    rungsseite
    -0.78
    DoubleQuotes
    -0.71
    aarrggbb
    -0.66
    InitVars
    -0.66
    脚注の使い方
    -0.65
    AsUp
    -0.64
    ]-->
    -0.64
     utafitiHapana
    -0.62
    richTextPanel
    -0.58
    POSITIVE LOGITS
    Zeneca
    0.60
     Granger
    0.50
     pizarra
    0.50
    piracy
    0.49
     judiciales
    0.49
    WireFormat
    0.48
    heide
    0.48
    angliski
    0.48
     infância
    0.48
     vastaan
    0.47
    Act Density 0.091%

    No Known Activations