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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of love and its various expressions

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

    love and affection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.57
    SourceChecksum
    -0.56
    haikusbot
    -0.54
    قایناقلار
    -0.52
     mockery
    -0.52
    nastics
    -0.51
    المكان
    -0.50
    annica
    -0.50
    adpleegd
    -0.48
     uska
    -0.47
    POSITIVE LOGITS
     loving
    0.50
     LOVE
    0.49
    love
    0.49
    LOVE
    0.48
     love
    0.47
     heart
    0.45
    Love
    0.43
     Love
    0.42
    爱
    0.41
     loves
    0.40
    Act Density 0.015%

    No Known Activations