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

    Neuronpedia

    INDEX
    Explanations

    semua kata sifat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nguyễn
    1.09
    મ્પ
    1.05
     და
    1.02
    Viet
    0.98
    комп
    0.98
    Ха
    0.97
    ரீ
    0.96
    Lä
    0.96
     호
    0.95
     Anh
    0.94
    POSITIVE LOGITS
    nya
    1.32
    anya
    1.30
     saja
    1.27
     sekali
    1.27
     seperti
    1.25
     yang
    1.24
    annya
    1.24
     ber
    1.19
     secara
    1.19
     serta
    1.17
    Act Density 0.014%

    No Known Activations