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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a level of exception or contrast

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

    even greater

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getMenuInflater
    -0.60
    complexContent
    -0.58
     AssemblyCulture
    -0.52
    出版年
    -0.48
    ConstraintMaker
    -0.47
     ویکی‌پدی
    -0.46
    transQ
    -0.46
     հղումներ
    -0.43
     aikana
    -0.42
    ChromeDriver
    -0.41
    POSITIVE LOGITS
    poň
    0.48
     définiti
    0.43
     draft
    0.42
     noDo
    0.42
    endish
    0.42
     moderately
    0.42
     Draft
    0.41
     fairly
    0.41
     modestly
    0.40
     remotely
    0.40
    Act Density 0.182%

    No Known Activations