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

    Neuronpedia

    INDEX
    Explanations

    superior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _exempt
    -0.07
    ीव
    -0.06
     inaug
    -0.06
     diplom
    -0.06
     trash
    -0.06
     Archive
    -0.06
     Brno
    -0.06
    chedules
    -0.06
     dishwasher
    -0.06
     Outreach
    -0.06
    POSITIVE LOGITS
    (qu
    0.08
     outweigh
    0.07
     JQuery
    0.07
     citing
    0.06
    �权
    0.06
    EF
    0.06
    _capability
    0.06
    量
    0.06
     امتی
    0.06
    /new
    0.06
    Act Density 0.044%

    No Known Activations