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

    Neuronpedia

    INDEX
    Explanations

    sequences of special characters or punctuation marks

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

    malformed unicode characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uldu
    -0.41
    retung
    -0.39
     tiada
    -0.38
    webElementGuid
    -0.38
     göre
    -0.37
     βα
    -0.37
     qualities
    -0.36
    দের
    -0.36
    rende
    -0.36
     udara
    -0.36
    POSITIVE LOGITS
    rungsseite
    0.72
     JpaRepository
    0.50
    KommentareTeilen
    0.50
    uxxxx
    0.50
    Datuak
    0.49
     disponibilités
    0.48
     Autorizaciones
    0.48
     nonUne
    0.48
     queſta
    0.48
     pleaſure
    0.48
    Act Density 0.192%

    No Known Activations