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

    Neuronpedia

    INDEX
    Explanations

    clauses containing conditional words regarding beliefs or moral issues, particularly in a political context

    oai_token-act-pair · gemini-2.0-flash

    Peace/religious beliefs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remove
    -0.75
     removal
    -0.72
     removing
    -0.71
     Remove
    -0.69
    remove
    -0.69
     Removing
    -0.67
     removes
    -0.65
     Removal
    -0.64
     removed
    -0.62
    Removing
    -0.61
    POSITIVE LOGITS
    +#+
    0.79
     conscientious
    0.71
    InputTagHelper
    0.65
     Conscience
    0.65
     conscience
    0.65
     Peace
    0.61
     peace
    0.60
    Peace
    0.60
    /*
    0.58
    stateProvider
    0.57
    Act Density 1.306%

    No Known Activations