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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to uncertainty, inquiry, and exploration of ideas

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

    a lack of information

    np_acts-logits-general · gemini-2.0-flash

    seeking how or why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.58
    BeginContext
    -0.56
    bootstrapcdn
    -0.55
    writeFieldEnd
    -0.54
    :✨
    -0.53
    TagMode
    -0.53
     resourceCulture
    -0.52
    expandindo
    -0.52
    بوابة
    -0.51
    BagLayout
    -0.50
    POSITIVE LOGITS
     how
    0.98
     what
    0.76
     DataTypes
    0.66
     why
    0.64
     siitä
    0.64
    how
    0.61
     whats
    0.59
     HOW
    0.57
    what
    0.57
    Попис
    0.56
    Act Density 0.296%

    No Known Activations