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

    Neuronpedia

    INDEX
    Explanations

    instances of mathematical notation or references to mathematical concepts

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

    mathematical notation with conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.59
     Bedür
    -0.54
    oa̍t
    -0.53
     betweenstory
    -0.52
    EndProject
    -0.51
    opportunity
    -0.51
     OPPORTUNITY
    -0.50
    ByVersion
    -0.49
    phòng
    -0.48
     disambiguazione
    -0.48
    POSITIVE LOGITS
    text
    1.41
     text
    1.10
    Text
    1.02
     Text
    0.97
    TEXT
    0.94
     textual
    0.77
     TEXT
    0.75
     texts
    0.72
     texto
    0.72
    \{\\
    0.66
    Act Density 0.010%

    No Known Activations