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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures related to data classification or labeling

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

    numbers, symbols, and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſind
    -0.86
     Verſ
    -0.79
     surla
    -0.75
     queſta
    -0.75
    ésultats
    -0.73
     utafitiHapana
    -0.73
     müſſen
    -0.73
    AddTagHelper
    -0.73
     indígen
    -0.72
    CppMethod
    -0.71
    POSITIVE LOGITS
    is
    0.45
     humains
    0.42
    Status
    0.40
    ’
    0.40
     duros
    0.39
    :
    0.38
    .
    0.38
    ID
    0.37
    k
    0.37
     with
    0.35
    Act Density 1.856%

    No Known Activations