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

    Neuronpedia

    INDEX
    Explanations

    terms related to privacy and security

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

    sensitive and private information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fix
    -0.33
    Fix
    -0.31
    enn
    -0.30
    light
    -0.30
     Remove
    -0.29
     Dan
    -0.29
    build
    -0.29
    org
    -0.29
    nn
    -0.29
     Bill
    -0.29
    POSITIVE LOGITS
     referrerpolicy
    0.73
    Personendaten
    0.65
    routeProvider
    0.64
    expandindo
    0.63
     privacy
    0.63
     security
    0.61
    Diweddarwch
    0.61
    twimg
    0.60
     confidentiality
    0.60
     Privacy
    0.59
    Act Density 0.130%

    No Known Activations