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

    Neuronpedia

    INDEX
    Explanations

    terms associated with mental health and well-being

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

    mental health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varandra
    -0.60
     marito
    -0.58
     tesettür
    -0.55
    แดง
    -0.54
     eşofman
    -0.52
     novios
    -0.52
     hırka
    -0.52
    HostException
    -0.49
     sayap
    -0.49
     Américas
    -0.49
    POSITIVE LOGITS
    Mental
    1.93
     mental
    1.91
     Mental
    1.87
     MENTAL
    1.69
    mental
    1.61
     mentally
    1.41
     mentale
    1.30
     mentales
    1.20
     Ment
    0.96
    Ment
    0.90
    Act Density 0.012%

    No Known Activations