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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation or expressions

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

    parsing code and configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hom
    -0.35
    ComponentName
    -0.35
    i
    -0.35
    P
    -0.33
    三
    -0.32
     near
    -0.32
    AccountNumber
    -0.31
     National
    -0.31
     ervan
    -0.31
     Min
    -0.30
    POSITIVE LOGITS
    parsedMessage
    0.92
    Personensuche
    0.92
     &___
    0.90
     resourceCulture
    0.89
     propOrder
    0.88
    :✨
    0.87
    存于互联网档案馆
    0.85
     surla
    0.84
    TagMode
    0.84
    IndentedString
    0.79
    Act Density 0.131%

    No Known Activations