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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers or characters organized with separators, indicating structured data or lists

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

    line numbers and code diffs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Canada
    -0.42
    ณ์
    -0.35
     interviewed
    -0.35
    Canada
    -0.34
    verhältnisse
    -0.34
    PullParser
    -0.33
    SOC
    -0.33
     bây
    -0.32
    contentView
    -0.32
     entrevistas
    -0.32
    POSITIVE LOGITS
    ftagPool
    0.81
    تقاوى
    0.75
    DoubleQuotes
    0.72
     disambiguazione
    0.68
    GTCX
    0.64
     surla
    0.63
     otomatig
    0.62
    WebVitals
    0.60
     <=",
    0.60
     betweenstory
    0.59
    Act Density 0.022%

    No Known Activations