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

    Neuronpedia

    INDEX
    Explanations

    any given time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Days
    0.51
     YEARS
    0.50
     Years
    0.50
    ⏳
    0.49
    Days
    0.48
    years
    0.46
    Years
    0.45
     roky
    0.44
    几年
    0.43
    Week
    0.42
    POSITIVE LOGITS
     moment
    1.33
     момент
    1.19
     momento
    1.05
    moment
    1.03
     moments
    0.99
     момента
    0.98
     momen
    0.93
     momenti
    0.91
     momencie
    0.90
     Moment
    0.88
    Act Density 0.029%

    No Known Activations