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

    Neuronpedia

    INDEX
    Explanations

    references to core values and character traits in individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Qualities, traits, or values

    np_acts-logits-general · gemini-2.0-flash

    virtues and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.68
     estekak
    -0.57
    PerformLayout
    -0.57
    ViewImports
    -0.57
    󠁮
    -0.54
     MotionEvent
    -0.54
    Tembelea
    -0.53
    UserScript
    -0.53
    moth
    -0.53
     समीक्षाओं
    -0.53
    POSITIVE LOGITS
     qualities
    0.96
     values
    0.96
     traits
    0.88
     Qualities
    0.83
     virtues
    0.82
     moral
    0.82
     valeurs
    0.80
     valores
    0.79
     Werte
    0.79
     Values
    0.78
    Act Density 0.263%

    No Known Activations