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

    Neuronpedia

    INDEX
    Explanations

    strings and identifiers related to programming and code elements, particularly focusing on social media and database interactions

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

    Non-English language fragments or characters

    np_acts-logits-general · gemini-2.0-flash

    language specific prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.49
     myſelf
    -1.48
     Efq
    -1.45
     pleaſure
    -1.43
     purpoſe
    -1.43
     Majefty
    -1.38
     ſche
    -1.37
     ainfi
    -1.36
     Jefus
    -1.35
     itſelf
    -1.34
    POSITIVE LOGITS
     le
    0.68
     en
    0.66
     d
    0.65
     de
    0.65
     l
    0.65
     del
    0.61
     na
    0.58
     o
    0.56
     dan
    0.56
     da
    0.55
    Act Density 0.572%

    No Known Activations