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

    Neuronpedia

    INDEX
    Explanations

    mental state

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Innovation
    0.58
     Cultures
    0.55
     स्वादिष्ट
    0.54
     أنواع
    0.52
     انواع
    0.51
    Innovation
    0.51
     Innovations
    0.51
     Theorems
    0.50
     Meaning
    0.50
     Foods
    0.49
    POSITIVE LOGITS
     psyche
    1.08
     demeanor
    1.07
     mental
    0.96
     wellbeing
    0.96
     finances
    0.94
     identity
    0.89
     physique
    0.88
     composure
    0.87
     abilities
    0.86
     demean
    0.86
    Act Density 0.560%

    No Known Activations