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

    Neuronpedia

    INDEX
    Explanations

    dramatic high intensity

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dem
    0.59
    Dem
    0.59
     accounts
    0.54
     Dem
    0.50
    Accounts
    0.50
     suggests
    0.45
    accounts
    0.45
    dem
    0.45
     Accounts
    0.45
     suggestions
    0.44
    POSITIVE LOGITS
     dramat
    0.55
     Dram
    0.48
     beautifully
    0.43
     spectacularly
    0.43
     dramatic
    0.42
     dramatically
    0.42
     DRAM
    0.42
     dram
    0.42
     high
    0.41
     High
    0.40
    Act Density 0.004%

    No Known Activations