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

    Neuronpedia

    INDEX
    Explanations

    over time or period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     years
    1.45
     Years
    1.23
    years
    1.21
     months
    1.20
    Years
    1.18
     Months
    1.15
     weeks
    1.13
     YEARS
    1.12
     decades
    1.08
     años
    1.08
    POSITIVE LOGITS
    period
    0.86
     span
    0.81
    grace
    0.79
    ለያዩ
    0.79
     finite
    0.79
     całym
    0.78
    course
    0.78
     intervalo
    0.78
    Period
    0.78
    given
    0.78
    Act Density 0.078%

    No Known Activations