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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     поступ
    -0.07
     myslí
    -0.07
     sæ
    -0.06
     объем
    -0.06
    服務
    -0.06
     πως
    -0.06
    >();
↵
    -0.06
     BJP
    -0.06
    ніше
    -0.06
    ози
    -0.06
    POSITIVE LOGITS
    ям
    0.07
    Red
    0.06
     رئ
    0.06
    \Auth
    0.06
    privileged
    0.06
     '^
    0.06
     Reading
    0.06
     Cathy
    0.06
     Remote
    0.06
     Observable
    0.06
    Act Density 0.001%

    No Known Activations