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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рам
    -0.07
    .fin
    -0.06
    -0.06
    される
    -0.06
    -Al
    -0.06
     efficiently
    -0.06
    scopic
    -0.06
     hydrated
    -0.06
     eser
    -0.06
     vot
    -0.06
    POSITIVE LOGITS
     �
    0.07
     Accessories
    0.07
     fisse
    0.06
     './../
    0.06
    邊
    0.06
    /temp
    0.06
    公路
    0.06
    阅读
    0.06
    dsn
    0.06
     تکن
    0.06
    Act Density 0.013%

    No Known Activations