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

    Neuronpedia

    INDEX
    Explanations

    security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (object
    -0.08
    美容
    -0.08
    Units
    -0.08
     સુંદર
    -0.08
    roscopic
    -0.07
    [T
    -0.07
    (
↵
    -0.07
     atrap
    -0.07
    _units
    -0.07
    (se
    -0.07
    POSITIVE LOGITS
     confidentiality
    0.10
     privacy
    0.09
     disclosure
    0.09
     confidentialité
    0.09
     privacidad
    0.09
     개인정보
    0.09
     spyware
    0.08
     NOAA
    0.08
    énom
    0.08
     സ്വകാര്യ
    0.08
    Act Density 0.001%

    No Known Activations