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

    Neuronpedia

    INDEX
    Explanations

    future generations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     направ
    0.35
     ১৯৬৫
    0.35
    aringan
    0.34
     knotted
    0.34
     perfected
    0.34
    দিকে
    0.33
     licking
    0.33
     instantaneously
    0.33
    ifically
    0.33
     cheered
    0.32
    POSITIVE LOGITS
     posterity
    1.51
     future
    1.50
     generations
    1.50
    future
    1.38
     generaciones
    1.34
     générations
    1.33
     Future
    1.28
    Future
    1.26
     futuras
    1.25
     Generations
    1.24
    Act Density 0.019%

    No Known Activations