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

    Neuronpedia

    INDEX
    Explanations

    references to returning or going back to previous content

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

    return to text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    氏
    -0.41
    omock
    -0.35
     arşivlendi
    -0.34
    uxxxx
    -0.34
     noDo
    -0.33
     ویکی‌پدیا
    -0.32
     氏
    -0.31
     fac
    -0.31
    uch
    -0.31
     DbSet
    -0.31
    POSITIVE LOGITS
    AddTagHelper
    0.60
     tillbaka
    0.59
     tilbage
    0.58
    IsMutable
    0.54
    IBarButtonItem
    0.53
     remonte
    0.52
    Terug
    0.50
    colgante
    0.50
    iprot
    0.50
    horesis
    0.50
    Act Density 0.029%

    No Known Activations