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

    Neuronpedia

    INDEX
    Explanations

    references to public-oriented topics and engagement

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

    public opinion, health, education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Карьера
    -0.49
     GenerationType
    -0.47
    makaian
    -0.41
    solo
    -0.40
     Geschw
    -0.39
     talentos
    -0.39
     sonhos
    -0.38
     bisnis
    -0.37
     Größen
    -0.37
    complexContent
    -0.36
    POSITIVE LOGITS
     Public
    0.76
     public
    0.75
    Public
    0.71
     publics
    0.66
     PUBLIC
    0.59
     publiques
    0.57
     públicas
    0.56
     pubb
    0.55
     publico
    0.54
    public
    0.50
    Act Density 0.013%

    No Known Activations