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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arom
    1.53
     Também
    1.51
    arag
    1.48
    ‌آ
    1.43
    ’’’’
    1.42
    Tổng
    1.41
    Tema
    1.39
    ară
    1.38
    Про
    1.38
    Voor
    1.38
    POSITIVE LOGITS
    ्स
    1.94
    ted
    1.81
    ti
    1.78
    ts
    1.70
    ться
    1.66
    tion
    1.58
    t
    1.54
    tn
    1.52
    てください
    1.52
    ),
    1.44
    Act Density 0.040%

    No Known Activations