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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

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

    Word after "I" or capitalized word

    np_acts-logits-general · gemini-2.0-flash

    possessives and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.08
     nahilalakip
    -0.93
     NSCoder
    -0.86
    AndEndTag
    -0.84
     JpaRepository
    -0.83
    ValueStyle
    -0.82
    bootstrapcdn
    -0.80
     تضيفلها
    -0.75
    دانشنامهٔ
    -0.73
     مشين
    -0.73
    POSITIVE LOGITS
    I
    0.48
    This
    0.45
    ství
    0.45
     bruges
    0.44
    Very
    0.43
    First
    0.42
     geweest
    0.42
     Besar
    0.42
     reciente
    0.40
     hernia
    0.40
    Act Density 0.024%

    No Known Activations