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

    Neuronpedia

    INDEX
    Explanations

    tokens that signify the beginning of a document or section

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

    Immediately after periods

    np_acts-logits-general · gemini-2.0-flash

    using or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.64
    PreInfinity
    -0.58
    べた
    -0.57
    eer
    -0.54
    ilized
    -0.53
     FontFamily
    -0.53
     hung
    -0.52
    totic
    -0.51
    reya
    -0.51
    aneous
    -0.51
    POSITIVE LOGITS
    ValueStyle
    0.91
     autorytatywna
    0.89
    :✨
    0.84
    تقاوى
    0.81
    الإنجليزية
    0.73
     Савезне
    0.73
     Roskov
    0.72
     nahilalakip
    0.70
     دیکھیے
    0.69
    Personendaten
    0.67
    Act Density 0.198%

    No Known Activations