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

    Neuronpedia

    INDEX
    Explanations

    adding richness and depth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extremadamente
    0.68
     આજ
    0.67
     পর্যবেক্ষণ
    0.66
    extremely
    0.66
     reallocation
    0.65
    ihanna
    0.65
    Survival
    0.64
     относительно
    0.64
     readjust
    0.63
     onChange
    0.63
    POSITIVE LOGITS
     depth
    1.89
     personality
    1.88
     richness
    1.71
     charm
    1.70
     vibrancy
    1.62
     warmth
    1.61
     substance
    1.59
     flavor
    1.55
     texture
    1.53
    depth
    1.52
    Act Density 0.362%

    No Known Activations