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

    Neuronpedia

    INDEX
    Explanations

    references to people falling in love and people who enjoy sports

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'love'

    np_token-act-pair-logits · gpt-4o-mini

    love

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出版年
    -0.57
     initComponents
    -0.56
     NSP
    -0.52
    jmniej
    -0.51
    dafx
    -0.51
     indisponible
    -0.50
    setVerticalGroup
    -0.48
     Scy
    -0.48
    colgroup
    -0.47
     egiten
    -0.46
    POSITIVE LOGITS
     love
    2.03
    love
    1.59
     Love
    1.52
    Love
    1.48
     LOVE
    1.44
    LOVE
    1.36
     loves
    1.33
     사랑
    1.09
     lov
    1.09
    loves
    1.08
    Act Density 0.972%

    No Known Activations