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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pend
    -0.08
    monkey
    -0.08
     wedge
    -0.08
    eta
    -0.08
    EUR
    -0.07
    acements
    -0.07
     חי
    -0.07
    backend
    -0.07
    erva
    -0.07
    drink
    -0.07
    POSITIVE LOGITS
    "This
    0.08
    农历
    0.07
     Lista
    0.07
     продол
    0.07
    ListAdapter
    0.07
    组织生活
    0.07
    list
    0.07
     Describe
    0.07
     ועד
    0.07
     notamment
    0.07
    Act Density 0.103%

    No Known Activations