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

    Neuronpedia

    INDEX
    Explanations

    an followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.63
    )
    1.51
    ের
    1.50
    жды
    1.45
    ),
    1.42
    sack
    1.39
    1.39
    ).
    1.38
    ないと
    1.30
    sheet
    1.28
    POSITIVE LOGITS
    ش
    2.34
    شون
    1.95
    ен
    1.88
    ন
    1.88
    на
    1.85
    વ
    1.84
    न
    1.81
    ки
    1.80
    ع
    1.73
     milliliters
    1.70
    Act Density 0.100%

    No Known Activations