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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NUM
    -0.07
     있었
    -0.07
     bump
    -0.07
    刻
    -0.07
     Bern
    -0.06
    Bern
    -0.06
     stunning
    -0.06
     Iterate
    -0.06
     activism
    -0.06
     поль
    -0.06
    POSITIVE LOGITS
    、小
    0.06
     adopts
    0.06
     Wireless
    0.06
     ingin
    0.06
     Universal
    0.06
    -lived
    0.06
     Aggregate
    0.06
    ablytyped
    0.06
    еріга
    0.06
    /Card
    0.06
    Act Density 0.013%

    No Known Activations