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

    Neuronpedia

    INDEX
    Explanations

    code snippets, programming, commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tolerances
    0.42
     consumable
    0.41
     adaptable
    0.40
     لحاظ
    0.40
     quais
    0.39
    各类
    0.39
     waahanga
    0.39
     bersifat
    0.39
     meliputi
    0.39
     tenuous
    0.39
    POSITIVE LOGITS
    movie
    0.46
    Movie
    0.44
    k
    0.44
    으로
    0.44
    z
    0.43
    show
    0.43
    x
    0.42
    to
    0.42
    news
    0.41
     mysql
    0.41
    Act Density 0.018%

    No Known Activations