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

    Neuronpedia

    INDEX
    Explanations

    duration or span

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fiatal
    0.50
     dietitian
    0.46
    教師
    0.45
     ব্যাকটেরিয়া
    0.45
     বয়স্ক
    0.45
    ध्यात्म
    0.45
    jahter
    0.45
     ग्रैंड
    0.44
     gyerek
    0.43
    llabus
    0.42
    POSITIVE LOGITS
    伏
    0.42
    所
    0.42
     usually
    0.39
     wymien
    0.39
     mentioned
    0.39
    成
    0.38
    usually
    0.38
    DURATION
    0.37
    Ó
    0.37
     span
    0.37
    Act Density 0.000%

    No Known Activations