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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and surnames

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

    names in legal contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.65
     kaarangay
    -0.60
    :✨
    -0.59
    ngdoc
    -0.59
     propOrder
    -0.58
    BeginContext
    -0.56
     &___
    -0.55
     Roskov
    -0.55
     ویکی‌پدی
    -0.54
    verifyException
    -0.53
    POSITIVE LOGITS
     Infór
    0.43
     vœux
    0.39
     Ejec
    0.37
    ∎
    0.34
     okuyayım
    0.33
    lectricité
    0.32
    AMILY
    0.32
     coucher
    0.31
     dîner
    0.31
     mascota
    0.31
    Act Density 0.009%

    No Known Activations