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

    Neuronpedia

    INDEX
    Explanations

    assist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ampling
    -0.06
    .training
    -0.06
    formance
    -0.06
     확
    -0.06
     Aero
    -0.06
    اتر
    -0.06
     Beds
    -0.06
    cona
    -0.06
     Pleasant
    -0.06
     البد
    -0.06
    POSITIVE LOGITS
    σει
    0.07
    [href
    0.07
    施
    0.07
     suggestive
    0.06
    _AD
    0.06
    isLoading
    0.06
     astounding
    0.06
     exist
    0.06
    reve
    0.06
     Persistent
    0.06
    Act Density 0.002%

    No Known Activations