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

    Neuronpedia

    INDEX
    Explanations

    parentheses, brackets, and comma separated lists in code syntax

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

    plot parameters and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.66
    transQ
    -0.63
    openzeppelin
    -0.60
    awtextra
    -0.59
     محفوظة
    -0.58
     queſta
    -0.58
     ſta
    -0.57
     EconPapers
    -0.56
    ſammen
    -0.55
     Reſ
    -0.54
    POSITIVE LOGITS
     חיצוניים
    0.35
     føl
    0.32
    ourites
    0.32
     alluminio
    0.31
    WebVitals
    0.30
     measured
    0.29
     dels
    0.28
    JSON
    0.28
    styleUrls
    0.28
     jungen
    0.27
    Act Density 0.004%

    No Known Activations