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

    Neuronpedia

    INDEX
    Explanations

    Object

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     medicine
    -0.07
     شه
    -0.07
     stun
    -0.06
    earch
    -0.06
     وي
    -0.06
     Portland
    -0.06
    .create
    -0.06
     svc
    -0.06
     Yale
    -0.06
     alan
    -0.06
    POSITIVE LOGITS
     adherence
    0.07
    ří
    0.07
     일부
    0.07
    CHE
    0.06
     dolar
    0.06
     ομά
    0.06
     ACCESS
    0.06
     انسان
    0.06
    604
    0.06
    asting
    0.06
    Act Density 0.005%

    No Known Activations