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

    Neuronpedia

    INDEX
    Explanations

    suggestions and what you can do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ि
    0.42
    視野
    0.42
    襯
    0.41
     )
    0.41
     t
    0.41
     s
    0.41
    試料
    0.41
    空格
    0.40
     x
    0.40
    底部
    0.40
    POSITIVE LOGITS
     možete
    0.61
    łości
    0.51
     uop
    0.47
     můžete
    0.47
    ക്കാം
    0.47
     uključ
    0.46
     możesz
    0.45
     môžete
    0.45
     জুড়ে
    0.44
     hton
    0.44
    Act Density 0.000%

    No Known Activations