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

    Neuronpedia

    INDEX
    Explanations

    your/my/our inner self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Careers
    0.73
     diets
    0.72
    careers
    0.72
    titles
    0.71
     surnames
    0.71
     Lösung
    0.69
    LogLevel
    0.69
    Careers
    0.69
     Types
    0.69
     Names
    0.68
    POSITIVE LOGITS
     soul
    1.32
     psyche
    1.23
     spirit
    1.13
     essence
    1.09
     existence
    1.09
     reality
    1.06
     persona
    1.03
     identity
    1.03
     inner
    1.00
     personality
    0.95
    Act Density 0.189%

    No Known Activations