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

    Neuronpedia

    INDEX
    Explanations

    Population size and evolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.41
    ۔
    1.15
    は
    1.01
    مس
    1.00
    یت
    0.96
    بد
    0.91
    ።
    0.89
    נ
    0.88
    માં
    0.88
    رد
    0.87
    POSITIVE LOGITS
    is
    1.29
     Population
    1.13
    ти
    1.13
    us
    1.05
     population
    1.05
    ן
    1.02
    те
    1.01
    ু
    0.98
    populations
    0.96
    0.95
    Act Density 0.014%

    No Known Activations