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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their placements in sentences

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

    Comes after a period

    np_acts-logits-general · gemini-2.0-flash

    demonstratives in various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.99
    Geplaatst
    -0.93
     AssemblyCulture
    -0.89
    AllAfrica
    -0.85
    WriteTagHelper
    -0.84
    extAlignment
    -0.84
     disambiguazione
    -0.82
    RTLD
    -0.80
     fieldNum
    -0.80
    UnknownFields
    -0.80
    POSITIVE LOGITS
     acesta
    0.51
    сюда
    0.43
     «
    0.42
    ↵
    0.42
     auxquels
    0.41
     After
    0.40
    After
    0.39
     căr
    0.39
     acestea
    0.39
     after
    0.39
    Act Density 0.197%

    No Known Activations