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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     releg
    -0.08
     việc
    -0.06
     exploited
    -0.06
     starvation
    -0.06
    mist
    -0.06
    =read
    -0.06
    agn
    -0.06
    AccountId
    -0.06
    .WebDriver
    -0.06
     hrs
    -0.06
    POSITIVE LOGITS
     original
    0.07
    others
    0.07
     pee
    0.07
    otionEvent
    0.07
     Rosenstein
    0.06
     unloaded
    0.06
     Tinder
    0.06
    inker
    0.06
    itere
    0.06
    imizde
    0.06
    Act Density 0.048%

    No Known Activations