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

    Neuronpedia

    INDEX
    Explanations

    obedience and submission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Intervention
    0.72
     density
    0.71
    Medicare
    0.71
     intervention
    0.71
     biodivers
    0.70
     interventions
    0.70
     pulmon
    0.70
     Density
    0.69
     ഇടപെ
    0.69
     discrimination
    0.68
    POSITIVE LOGITS
     obedient
    2.10
     obey
    1.89
     obedience
    1.79
    obedience
    1.72
     subserv
    1.72
     Obed
    1.68
     obed
    1.66
     docile
    1.66
     surrender
    1.64
     obeyed
    1.63
    Act Density 0.456%

    No Known Activations