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

    Neuronpedia

    INDEX
    Explanations

    quantities of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    取り組み
    0.58
    的做法
    0.57
     dealings
    0.52
     storytelling
    0.50
     подход
    0.50
     ഇടപെ
    0.49
    approach
    0.49
     प्रयासों
    0.49
     atuação
    0.49
     შემთხვევ
    0.47
    POSITIVE LOGITS
    东西
    0.58
     wares
    0.51
     stuff
    0.48
    嘢
    0.47
    東西
    0.46
    Requ
    0.46
     quantità
    0.46
     ponownie
    0.45
    的东西
    0.43
     things
    0.43
    Act Density 0.046%

    No Known Activations