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

    Neuronpedia

    INDEX
    Explanations

    go-to, closest, most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    жность
    0.50
     ব্যবসার
    0.45
     없고
    0.43
    厛
    0.43
    勮
    0.42
     फैक्टर
    0.42
     Crime
    0.42
     Dire
    0.41
     এগুলো
    0.41
     Dept
    0.41
    POSITIVE LOGITS
     worldwide
    0.61
    worldwide
    0.58
     weltweit
    0.54
    ."
    0.54
    。
    0.54
    而在
    0.52
    .,
    0.50
    .”
    0.50
    日本では
    0.50
     today
    0.50
    Act Density 0.003%

    No Known Activations