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

    Neuronpedia

    INDEX
    Explanations

    to mental wellbeing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fallait
    0.70
     Diffraction
    0.64
     razlik
    0.61
     Errors
    0.60
     försö
    0.60
     velocità
    0.60
    डेड
    0.59
    尷
    0.59
    Split
    0.59
     Incorrect
    0.59
    POSITIVE LOGITS
     prosperity
    2.10
     happiness
    2.08
     wellbeing
    1.98
     welfare
    1.87
     economic
    1.78
     bienestar
    1.76
     social
    1.73
     socioeconomic
    1.67
    prosperity
    1.66
    happiness
    1.62
    Act Density 0.802%

    No Known Activations