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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in various contexts

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

    Comes after "S.", "U.S.", or "."

    np_acts-logits-general · gemini-2.0-flash

    . Ct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     id
    -0.61
    [
    -0.59
    -
    -0.57
    iser
    -0.56
     art
    -0.56
     ed
    -0.54
     city
    -0.53
     night
    -0.53
     sub
    -0.52
     block
    -0.52
    POSITIVE LOGITS
    AddTagHelper
    0.61
    ContentAsync
    0.59
     MessageBoxIcon
    0.58
    κτηρισ
    0.57
    prefixer
    0.57
     triom
    0.56
    󠁴
    0.55
    AutoresizingMask
    0.55
     chargés
    0.52
    endsection
    0.52
    Act Density 0.027%

    No Known Activations