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

    Neuronpedia

    INDEX
    Explanations

    expressions of love and affection within relationships

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

    love for people or things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XHR
    -0.34
    IVEREF
    -0.34
     Quelle
    -0.33
     enquiries
    -0.33
     Gunung
    -0.32
     enqu
    -0.32
    glLoad
    -0.32
    "/",
    -0.32
     entrants
    -0.31
    Parmi
    -0.31
    POSITIVE LOGITS
    loves
    0.69
    Love
    0.69
    love
    0.68
     Loves
    0.68
     LOVE
    0.68
     love
    0.67
     loves
    0.67
     Love
    0.66
    RegressionTest
    0.65
     älskar
    0.65
    Act Density 0.011%

    No Known Activations