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

    Neuronpedia

    INDEX
    Explanations

    scientific/academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    家伙
    -0.07
    _person
    -0.07
    .prop
    -0.07
     GAME
    -0.06
    -finals
    -0.06
    ané
    -0.06
     наук
    -0.06
     Players
    -0.06
     hired
    -0.06
     Ahmed
    -0.06
    POSITIVE LOGITS
    -basic
    0.06
    omit
    0.06
    　�
    0.06
    analytics
    0.06
     )
    0.06
    tableFuture
    0.05
    paging
    0.05
     ViewBag
    0.05
     DERP
    0.05
    ัตว
    0.05
    Act Density 0.066%

    No Known Activations