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

    Neuronpedia

    INDEX
    Explanations

    stereotype component/service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Legacy
    0.44
     Flex
    0.41
     Freight
    0.41
     Morm
    0.41
     стоимо
    0.40
     Cavan
    0.40
    फुल
    0.39
     Fre
    0.39
     Cav
    0.38
    AG
    0.37
    POSITIVE LOGITS
     ঘরে
    0.38
    ตาย
    0.37
    🌒
    0.37
     enter
    0.36
    টাকে
    0.35
     interferes
    0.35
    ковый
    0.35
     বানিয়ে
    0.35
     interfering
    0.35
    simile
    0.35
    Act Density 0.000%

    No Known Activations