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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    она
    -0.06
     Palestinians
    -0.06
     tộc
    -0.06
    优秀
    -0.06
    ereotype
    -0.06
    ्रपत
    -0.06
     Бол
    -0.06
     воздуха
    -0.06
     comparing
    -0.06
    /train
    -0.05
    POSITIVE LOGITS
     AVR
    0.07
     DatePicker
    0.06
     burger
    0.06
     kaps
    0.06
     Pen
    0.06
    ek
    0.06
     Esp
    0.06
    tes
    0.06
    &_
    0.06
    ेण
    0.06
    Act Density 0.006%

    No Known Activations