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

    Neuronpedia

    INDEX
    Explanations

    descriptions of affection and love in relationships

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

    loving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portail
    -0.68
    lastIndex
    -0.57
     SUDOC
    -0.57
    PreExecute
    -0.56
     quæ
    -0.53
    TempData
    -0.52
    tableFuture
    -0.52
     Portail
    -0.50
     musk
    -0.50
    majánló
    -0.50
    POSITIVE LOGITS
     Loving
    0.75
    Loving
    0.71
    loving
    0.65
     loving
    0.59
     lovingly
    0.53
    olesome
    0.51
    volent
    0.47
    urous
    0.47
    hending
    0.44
    lovin
    0.44
    Act Density 0.004%

    No Known Activations