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

    Neuronpedia

    INDEX
    Explanations

    interjections and conjunctions in various languages

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

    French text after commas and "et"

    np_acts-logits-general · gemini-2.0-flash

    French conjunction 'et'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.06
     Efq
    -1.06
     raiſ
    -1.05
     purpoſe
    -1.02
     houſe
    -1.00
     pleaſure
    -0.99
     ſtate
    -0.97
     iſt
    -0.97
     ſta
    -0.97
     Theſe
    -0.97
    POSITIVE LOGITS
     in
    0.49
    XmlEnum
    0.45
    o
    0.43
     sekaligus
    0.43
     o
    0.42
    는
    0.41
     साथ
    0.41
     as
    0.41
    protoimpl
    0.41
     at
    0.41
    Act Density 0.040%

    No Known Activations