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

    Neuronpedia

    INDEX
    Explanations

    terms related to data structuring and types in various contexts

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

    directional adjectives, ordinals, or prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.80
     kaarangay
    -0.75
    Geplaatst
    -0.68
     surla
    -0.66
     lumineuse
    -0.60
     ویکی‌پدی
    -0.58
     torner
    -0.57
    lossians
    -0.56
     cœurs
    -0.56
    elemField
    -0.55
    POSITIVE LOGITS
    KommentareTeilen
    0.65
    ‍♂️
    0.51
    nonumber
    0.50
    */)
    0.50
    principalTable
    0.50
    ../../
    0.49
    --)
    0.49
    URLEncoder
    0.49
     versions
    0.48
    ингл
    0.47
    Act Density 0.156%

    No Known Activations