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

    Neuronpedia

    INDEX
    Explanations

    love, romance, affection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rubber
    0.46
     επο
    0.44
    opaque
    0.43
    rag
    0.42
    Time
    0.41
    Tempo
    0.40
    align
    0.40
    iox
    0.40
    automatic
    0.40
    unsubscribe
    0.40
    POSITIVE LOGITS
     love
    0.97
     💕
    0.93
     ❤️
    0.92
     ❤
    0.91
     LOVE
    0.85
    ❤️❤️
    0.83
     Love
    0.81
     사랑
    0.79
    ❤❤
    0.78
    LOVE
    0.77
    Act Density 0.027%

    No Known Activations