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

    Neuronpedia

    INDEX
    Explanations

    elements related to privacy and personal data protection

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

    personal date and credentials

    np_acts-logits-general · gemini-2.5-flash-lite

    statements about confidentiality or privacy that restrict sharing, publishing, or public access to information or personal data.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     czeka
    -0.42
     étanche
    -0.38
     colchón
    -0.38
     informée
    -0.35
     transparencia
    -0.35
     zamów
    -0.35
     plegable
    -0.35
     devra
    -0.35
     fédéral
    -0.35
     quiera
    -0.35
    POSITIVE LOGITS
    SharedCtor
    0.59
    nationality
    0.57
    GEBURTSDATUM
    0.56
     ProtoMessage
    0.55
    kháu
    0.52
    Посилання
    0.51
    llingwood
    0.51
     يتيمه
    0.50
    adaptiveStyles
    0.50
    ChildScrollView
    0.49
    Act Density 0.076%

    No Known Activations