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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and mathematical operations

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

    code keywords and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.61
    complexContent
    -0.59
    RTCK
    -0.57
    GEBURTSDATUM
    -0.56
     Мексичка
    -0.56
     AssemblyCulture
    -0.55
     Meksiku
    -0.53
    parsedMessage
    -0.52
     yym
    -0.52
     Normdatei
    -0.52
    POSITIVE LOGITS
     banget
    0.46
    ulaski
    0.36
    black
    0.35
    quinho
    0.35
     Deck
    0.34
     Haushalt
    0.33
    Aussie
    0.33
    AndEndTag
    0.33
    butik
    0.33
    ubby
    0.33
    Act Density 0.014%

    No Known Activations