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

    Neuronpedia

    INDEX
    Explanations

    specific entities and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mou
    0.39
    映
    0.39
    лье
    0.37
     deeds
    0.36
    Flights
    0.36
     mou
    0.36
     ling
    0.36
    HashMap
    0.35
     ezt
    0.35
     expiring
    0.35
    POSITIVE LOGITS
     Kamane
    0.41
    clusión
    0.40
     Peso
    0.38
     Gold
    0.38
     Strait
    0.38
    uldron
    0.37
    allowSlide
    0.37
     Stream
    0.37
     Walmart
    0.37
    кри
    0.37
    Act Density 0.000%

    No Known Activations