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

    Neuronpedia

    INDEX
    Explanations

    gaining knowledge or understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    如果你
    0.57
     यदि
    0.55
    如果您
    0.49
    Pokud
    0.49
    et
    0.49
    任何
    0.47
     অথবা
    0.46
    如果在
    0.45
    iem
    0.45
     qualsiasi
    0.44
    POSITIVE LOGITS
    知道了
    0.66
    有了
    0.62
     know
    0.57
     knowing
    0.57
     conocemos
    0.57
    才知道
    0.53
    してみて
    0.53
    知道
    0.52
     biết
    0.52
     hindsight
    0.49
    Act Density 0.039%

    No Known Activations