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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confidentiality and the protection of personal information

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

    Confidentiality and anonymity

    np_acts-logits-general · gemini-2.0-flash

    confidentiality and anonymity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ணை
    -0.54
    ChildScrollView
    -0.47
    存于互联网档案馆
    -0.47
    supset
    -0.46
     بيها
    -0.44
     Dietz
    -0.44
     kuliah
    -0.43
    protoimpl
    -0.42
    AnchorTagHelper
    -0.42
    обре
    -0.42
    POSITIVE LOGITS
     confidentiality
    2.04
     confidential
    1.83
     privacy
    1.83
     secrecy
    1.79
     Confidentiality
    1.76
     anonymity
    1.73
     Confidential
    1.67
    Confidential
    1.57
     secret
    1.52
     Privacy
    1.51
    Act Density 0.392%

    No Known Activations