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

    Neuronpedia

    INDEX
    Explanations

    references to health and lifestyle, particularly focusing on the concept of being healthy

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

    health and unhealth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.46
    contentLoaded
    -0.43
     couvre
    -0.43
     ujednoznacz
    -0.41
     vectorielle
    -0.41
     незавершена
    -0.40
    那样
    -0.39
    KURZBESCHREIBUNG
    -0.38
     Ewig
    -0.38
    hbs
    -0.36
    POSITIVE LOGITS
    Healthy
    1.08
     healthy
    1.07
    healthy
    1.00
     Healthy
    0.93
     saudável
    0.85
     unhealthy
    0.85
     healthiest
    0.80
     gesunde
    0.78
     saludable
    0.76
     healthier
    0.75
    Act Density 0.016%

    No Known Activations