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

    Neuronpedia

    INDEX
    Explanations

    integration testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .abstract
    -0.06
    }></
    -0.06
     музы
    -0.06
     ld
    -0.06
    _REASON
    -0.06
     bus
    -0.06
     anesthesia
    -0.06
    师
    -0.06
     Rout
    -0.06
     Wu
    -0.06
    POSITIVE LOGITS
    -за
    0.07
     поль
    0.07
     еще
    0.07
    όρ
    0.07
     además
    0.06
    Leader
    0.06
    ække
    0.06
     customers
    0.06
    ApiClient
    0.06
     όλ
    0.06
    Act Density 0.023%

    No Known Activations