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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases indicating proof, assumptions, or conclusions in a mathematical context

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

    we have that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.85
     للاسماء
    -0.69
     queſta
    -0.68
    ésultats
    -0.65
     itſelf
    -0.58
     فريبيس
    -0.57
     Biôgrafia
    -0.57
     ostavi
    -0.57
    Derbyniad
    -0.56
     jScrollPane
    -0.55
    POSITIVE LOGITS
    EditorBrowsable
    0.41
    assertEquals
    0.40
     sabemos
    0.38
     Since
    0.37
    onChange
    0.37
    tahui
    0.36
    :
    0.35
    Since
    0.35
    AddWithValue
    0.33
     sillä
    0.33
    Act Density 0.152%

    No Known Activations