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

    Neuronpedia

    INDEX
    Explanations

    cannot and will not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Capacity
    0.69
     Base
    0.62
     khoảng
    0.61
     head
    0.61
    ヘッド
    0.60
     full
    0.60
     jef
    0.60
     পারে
    0.60
     Full
    0.59
     Mult
    0.59
    POSITIVE LOGITS
     bhan
    0.69
    ż
    0.66
     rodr
    0.62
     பாம்பு
    0.61
     puppy
    0.61
     সেপ্টেম্বর
    0.61
    pyrazin
    0.60
    ZW
    0.60
     Hahn
    0.60
    BST
    0.59
    Act Density 0.147%

    No Known Activations