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

    Neuronpedia

    INDEX
    Explanations

    confidentiality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    edDevice
    0.40
     shawl
    0.40
    aternal
    0.38
    Hence
    0.38
    спубли
    0.38
     கிடை
    0.37
     activos
    0.37
     Constant
    0.37
     постоянно
    0.37
     постоян
    0.37
    POSITIVE LOGITS
     confidentiality
    0.99
     confidential
    0.99
     Confidential
    0.87
     anonymity
    0.74
     anonym
    0.73
     anonymous
    0.70
     confidentialité
    0.68
     गोपनीय
    0.68
    anonymous
    0.68
     secrecy
    0.67
    Act Density 0.016%

    No Known Activations