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

    Neuronpedia

    INDEX
    Explanations

    for me or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     někter
    0.41
    rictions
    0.40
    த்துறை
    0.40
    一般的
    0.40
    بعض
    0.40
     definitely
    0.39
     بعض
    0.38
     niektor
    0.38
     apparently
    0.37
     некоторых
    0.37
    POSITIVE LOGITS
    用于
    0.56
     students
    0.54
     kids
    0.53
     beginners
    0.50
     用于
    0.48
    для
    0.46
     KIDS
    0.46
    Для
    0.46
     purposes
    0.45
    สำหรับการ
    0.45
    Act Density 0.006%

    No Known Activations