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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions related to love and affection

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

    Text containing the word "heart"

    np_acts-logits-general · gemini-2.0-flash

    heart and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.60
    醐
    -0.56
     للاسماء
    -0.54
     Tosh
    -0.51
    ſelf
    -0.50
     agres
    -0.47
     XNUMX
    -0.46
     pleaſure
    -0.46
     deſt
    -0.45
     Houſe
    -0.45
    POSITIVE LOGITS
     heart
    2.52
     hearts
    2.30
    heart
    2.09
     Heart
    2.03
    Heart
    1.99
     HEART
    1.91
     corazón
    1.83
     Hearts
    1.76
    HEART
    1.73
    hearts
    1.70
    Act Density 0.262%

    No Known Activations