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

    Neuronpedia

    INDEX
    Explanations

    loving and affectionate connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     minimalism
    0.39
    omicron
    0.38
    }=-
    0.38
    plicial
    0.37
    edale
    0.36
     freezed
    0.36
     hemolysis
    0.36
    ίος
    0.35
    )=-\
    0.35
    لاسه
    0.35
    POSITIVE LOGITS
     loving
    2.19
     affectionate
    2.14
     affection
    1.79
    loving
    1.73
    affection
    1.69
     Loving
    1.67
    Loving
    1.64
     lovingly
    1.63
     tender
    1.60
     caring
    1.54
    Act Density 0.132%

    No Known Activations