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

    Neuronpedia

    INDEX
    Explanations

    terms related to privacy and protection of personal information

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

    protecting rights, property, public, and integrity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.54
    itri
    -0.43
    AddHtmlAttribute
    -0.40
    bels
    -0.40
    rew
    -0.40
    totic
    -0.39
    urro
    -0.38
     aapt
    -0.38
    tructor
    -0.38
    nter
    -0.37
    POSITIVE LOGITS
    protect
    0.92
     protect
    0.87
     PROTECT
    0.85
     protects
    0.85
     protecting
    0.82
    Protect
    0.79
    Protecting
    0.79
     protéger
    0.74
     protected
    0.74
    prote
    0.74
    Act Density 0.044%

    No Known Activations