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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers or codes

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

    numbers followed by specific punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    brock
    -0.45
    ḇ
    -0.43
     Blume
    -0.42
     BRANCH
    -0.42
    حياتها
    -0.41
     BRO
    -0.41
     Welle
    -0.41
     Legge
    -0.40
     Brot
    -0.40
     Abb
    -0.39
    POSITIVE LOGITS
     Италијани
    0.59
    AndEndTag
    0.54
    ymce
    0.54
    MessageOf
    0.54
    hamshire
    0.53
     MenuView
    0.52
     GNP
    0.50
    parsedMessage
    0.50
    chymal
    0.50
     Eigent
    0.50
    Act Density 0.209%

    No Known Activations