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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hled
    -0.07
    ieres
    -0.07
    datatype
    -0.06
     Exhibit
    -0.06
     uterus
    -0.06
     Über
    -0.06
    IL
    -0.06
    وح
    -0.06
     caregiver
    -0.06
     passenger
    -0.06
    POSITIVE LOGITS
    ，可
    0.07
    stagram
    0.07
     جم
    0.07
    -local
    0.06
     �
    0.06
     مات
    0.06
     predis
    0.06
     Nov
    0.06
     :/:
    0.06
     Kavanaugh
    0.06
    Act Density 0.130%

    No Known Activations