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

    Neuronpedia

    INDEX
    Explanations

    self-care activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    放松
    0.50
     distractions
    0.45
    iance
    0.45
     calma
    0.44
     strategies
    0.44
     supermarkets
    0.43
     televiz
    0.43
     relaxing
    0.42
     relax
    0.41
     evenings
    0.41
    POSITIVE LOGITS
     musical
    0.52
     laughing
    0.52
    Prec
    0.49
     hugging
    0.47
     deftly
    0.46
     nature
    0.46
    Dawn
    0.45
    Musical
    0.45
     Pri
    0.44
    꺅
    0.44
    Act Density 0.025%

    No Known Activations