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

    Neuronpedia

    INDEX
    Explanations

    recommending based on taste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     procedures
    0.47
     designing
    0.46
     unusable
    0.45
     implemented
    0.44
     livestock
    0.44
     implement
    0.44
     implementing
    0.43
     usable
    0.43
     infrastructure
    0.42
     governing
    0.42
    POSITIVE LOGITS
     추천
    0.81
     Geschmack
    0.79
    推荐
    0.77
     Recommendation
    0.75
     recomendar
    0.74
     жан
    0.73
     rekomend
    0.73
    Taste
    0.73
     Goodreads
    0.73
     tastes
    0.73
    Act Density 0.015%

    No Known Activations