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

    Neuronpedia

    INDEX
    Explanations

    names and amendments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    酚
    0.33
    铎
    0.32
     成分
    0.32
    Geography
    0.30
    FAQs
    0.30
     раствора
    0.29
    Nodes
    0.29
    Dogs
    0.29
    視頻
    0.29
    Bread
    0.29
    POSITIVE LOGITS
     Send
    0.31
     deficit
    0.31
    expected
    0.30
     Ny
    0.29
     Spend
    0.29
     Reserve
    0.29
    deficit
    0.29
     ouvrir
    0.28
     ●
    0.27
     Steele
    0.26
    Act Density 0.000%

    No Known Activations