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

    Neuronpedia

    INDEX
    Explanations

    with a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ToCheck
    0.32
    toNumber
    0.31
    authority
    0.31
     정보를
    0.31
    σει
    0.30
    lük
    0.30
    nisse
    0.30
     جناح
    0.30
    kým
    0.29
    ToReference
    0.29
    POSITIVE LOGITS
     একজন
    0.35
    一个
    0.34
     একটি
    0.32
    একটি
    0.31
    YOUR
    0.31
     unui
    0.30
     an
    0.29
     YOUR
    0.29
    ự
    0.29
    0.29
    Act Density 0.002%

    No Known Activations