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

    Neuronpedia

    INDEX
    Explanations

    Chinese concepts and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.80
    et
    0.79
    w
    0.74
     изменение
    0.73
    ១
    0.70
    to
    0.70
     измене
    0.69
    t
    0.69
    0.69
    n
    0.68
    POSITIVE LOGITS
    :
    0.63
    。
    0.62
    .
    0.61
     haven
    0.60
     camaraderie
    0.57
     thoughtful
    0.56
     backyard
    0.52
    ):
    0.52
    ，
    0.52
     gym
    0.52
    Act Density 0.059%

    No Known Activations