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

    Neuronpedia

    INDEX
    Explanations

    extrapolating time periods or durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ला
    1.56
    לים
    1.29
    l
    1.27
    ع
    1.13
    d
    1.12
    Aluminum
    1.10
    b
    1.09
     및
    1.06
    ल
    1.05
    ت
    1.05
    POSITIVE LOGITS
     фаразлары
    1.09
    годи
    1.07
    нит
    1.02
    profitLoss
    1.02
    onin
    1.01
    <unused2221>
    1.00
    year
    0.99
    🕙
    0.99
    憶
    0.99
    years
    0.98
    Act Density 0.126%

    No Known Activations