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

    Neuronpedia

    INDEX
    Explanations

    the start of different sections or paragraphs in documents, indicated by the presence of a specific token

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

    list elements following commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     newOwner
    -0.80
     CHtml
    -0.75
     Taktlose
    -0.68
    SourceChecksum
    -0.68
    addGap
    -0.66
    WebElementEntity
    -0.63
     onData
    -0.63
    OGND
    -0.63
    StoreMessageInfo
    -0.61
     iprot
    -0.60
    POSITIVE LOGITS
     Friday
    0.73
     Saturday
    0.73
    aturday
    0.71
     Fridays
    0.66
     evenings
    0.65
     weekend
    0.63
     Saturdays
    0.63
     Thursday
    0.63
     Wednesday
    0.63
     Wednesdays
    0.62
    Act Density 0.024%

    No Known Activations