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

    Neuronpedia

    INDEX
    Explanations

    years and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ating
    1.72
     quirúrg
    1.58
     pikir
    1.58
     Foi
    1.54
    ap
    1.52
    .
    1.52
    ້ມ
    1.50
    ⃙
    1.50
    ança
    1.49
    তিনি
    1.48
    POSITIVE LOGITS
    स
    1.89
     acquisitions
    1.86
     exons
    1.84
    恐怕
    1.70
     entrees
    1.49
    hdf
    1.48
     thiểu
    1.48
    𝗚
    1.48
     appointees
    1.48
    𝗔
    1.48
    Act Density 0.118%

    No Known Activations