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

    Neuronpedia

    INDEX
    Explanations

    HTML form element attributes and metadata

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

    Followed by equals sign(s)

    np_acts-logits-general · gemini-2.0-flash

    name values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.98
     '\\;'
    -0.82
     ویکی‌پدیا
    -0.73
    IsContent
    -0.71
    $_['
    -0.67
    PreferredItem
    -0.65
    Geplaatst
    -0.63
    AutoScaleMode
    -0.61
     trajets
    -0.60
    InstrumentedTest
    -0.59
    POSITIVE LOGITS
     кӀ
    0.61
    setVerticalGroup
    0.59
     asupra
    0.50
     متعلقه
    0.49
    WAR
    0.49
    ksom
    0.48
    nye
    0.48
     warmest
    0.48
    اء
    0.48
    gelöst
    0.47
    Act Density 0.082%

    No Known Activations