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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to data, metrics, and their implications in various contexts

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

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.77
    Autoritní
    -0.77
     nahilalakip
    -0.73
    Референце
    -0.65
    ंदीखरीदारी
    -0.62
    KommentareTeilen
    -0.59
    setVerticalGroup
    -0.57
    devamını
    -0.55
    BeginInit
    -0.54
     autorytatywna
    -0.54
    POSITIVE LOGITS
     segredo
    0.43
     koszulka
    0.42
     küche
    0.40
     perfección
    0.35
     avoient
    0.35
     muere
    0.35
     feroit
    0.34
    جغرافيا
    0.34
     femininos
    0.33
     materiales
    0.33
    Act Density 0.557%

    No Known Activations