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

    Neuronpedia

    INDEX
    Explanations

    I really

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     liking
    0.65
     nice
    0.53
     attractive
    0.50
     satisfactory
    0.48
    Nice
    0.47
    attractive
    0.47
     distaste
    0.47
    Acknowledgment
    0.47
     Nice
    0.46
    nice
    0.46
    POSITIVE LOGITS
     absolutely
    1.12
     absolutamente
    0.97
    absolutely
    0.91
     absolument
    0.91
     adored
    0.87
     assolutamente
    0.86
     Absolutely
    0.86
    Absolutely
    0.85
     абсолютно
    0.84
     eagerly
    0.82
    Act Density 0.056%

    No Known Activations