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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uš
    -0.06
     minimized
    -0.06
     Jen
    -0.06
    /cards
    -0.06
     Vacuum
    -0.06
    -ch
    -0.06
     complexity
    -0.06
    /dis
    -0.06
    redux
    -0.06
     Schul
    -0.06
    POSITIVE LOGITS
    )set
    0.07
     refere
    0.07
    Oregon
    0.06
    ）。↵
    0.06
     ліс
    0.06
    [__
    0.06
     услуг
    0.06
    pliant
    0.06
     έχουν
    0.06
     {*
    0.06
    Act Density 0.013%

    No Known Activations