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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical or logical sequences

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

    Mathematical or programming-related notation

    np_acts-logits-general · gemini-2.0-flash

    statistical and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.70
     and
    -0.61
    <eos>
    -0.61
    ,
    -0.60
     (
    -0.58
     i
    -0.57
     I
    -0.56
     R
    -0.55
     for
    -0.55
     or
    -0.54
    POSITIVE LOGITS
    yntaxException
    1.25
     дописавши
    1.24
    Vidite
    1.23
    Geplaatst
    1.22
    IsMutable
    1.20
     مرئيه
    1.18
    sizeCache
    1.17
    Datuak
    1.14
    GeoNames
    1.14
    CloseOperation
    1.14
    Act Density 0.925%

    No Known Activations