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

    Neuronpedia

    INDEX
    Explanations

    informing or guiding people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (""))
    0.32
     pyram
    0.28
    isième
    0.28
     molybdenum
    0.28
     Alsace
    0.27
     fleste
    0.27
     রসের
    0.27
    สาร
    0.27
     boson
    0.27
     idols
    0.27
    POSITIVE LOGITS
     people
    0.48
    人们
    0.47
     investors
    0.43
    人們
    0.42
    大家
    0.40
     लोगों
    0.39
    你
    0.39
     users
    0.38
    用户
    0.38
     employers
    0.38
    Act Density 0.184%

    No Known Activations