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

    Neuronpedia

    INDEX
    Explanations

    programming declarations and data types

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

    math symbols and non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tainable
    -0.42
     disambiguazione
    -0.41
     맞
    -0.40
    al
    -0.39
    ally
    -0.37
     Sosial
    -0.36
    viable
    -0.36
    falle
    -0.36
     available
    -0.35
    IVEREF
    -0.35
    POSITIVE LOGITS
    :✨
    0.58
     Biôgrafia
    0.55
     ویکی‌پدی
    0.55
     lenker
    0.54
    ArrowToggle
    0.53
    tanleria
    0.51
     CanadaChoose
    0.50
    ագրություններ
    0.49
    reactstrap
    0.48
     препратки
    0.48
    Act Density 0.006%

    No Known Activations