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

    Neuronpedia

    INDEX
    Explanations

    what did you do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prove
    0.48
    最終
    0.46
     luxe
    0.46
     deliverables
    0.44
    why
    0.43
    ड्स
    0.43
    ႃႇ
    0.43
    Prove
    0.42
    뒤
    0.42
    uose
    0.41
    POSITIVE LOGITS
    অথ
    0.46
     अपेक्षाकृत
    0.46
     conversation
    0.45
    的人
    0.45
     people
    0.44
     القرآن
    0.44
     Firefox
    0.43
     Robert
    0.43
     Quran
    0.43
     someone
    0.43
    Act Density 0.006%

    No Known Activations