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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences and structured data patterns

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

    numbers and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     after
    -0.41
     often
    -0.38
     always
    -0.36
     thoroughly
    -0.35
     usein
    -0.35
     increasingly
    -0.34
    eamiento
    -0.33
     dinámico
    -0.33
     frequently
    -0.32
     also
    -0.32
    POSITIVE LOGITS
    AddTagHelper
    0.67
    findpost
    0.67
    expandindo
    0.65
     ویکی‌پدی
    0.63
    tableFuture
    0.62
    GEBURTSDATUM
    0.59
    igshid
    0.58
    saraba
    0.58
    parsedMessage
    0.57
    featureID
    0.56
    Act Density 0.507%

    No Known Activations