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

    Neuronpedia

    INDEX
    Explanations

    data privacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Semester
    -0.09
    .skill
    -0.09
    品
    -0.08
     Semester
    -0.08
    Spacing
    -0.08
     Projectile
    -0.08
     星期
    -0.08
     Railway
    -0.08
    ）,
    -0.07
     Powder
    -0.07
    POSITIVE LOGITS
     privacy
    0.20
    Privacy
    0.19
     Privacy
    0.18
    privacy
    0.18
    /privacy
    0.17
     Datenschutz
    0.17
     privacidad
    0.17
     개인정보
    0.15
     GDPR
    0.15
     confidentialité
    0.13
    Act Density 0.063%

    No Known Activations