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

    Neuronpedia

    INDEX
    Explanations

    improve, better, more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relatively
    0.59
     unlike
    0.58
    unlike
    0.53
    relatively
    0.52
     Unlike
    0.52
    Unlike
    0.51
     comparatively
    0.50
     Relatively
    0.49
     relativamente
    0.46
     Gegensatz
    0.43
    POSITIVE LOGITS
     улуч
    1.50
     improved
    1.48
    มากขึ้น
    1.46
    更好的
    1.45
     mejorar
    1.44
     melhorar
    1.40
     verbeter
    1.37
     మరింత
    1.37
     improve
    1.36
     المزيد
    1.36
    Act Density 0.072%

    No Known Activations