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

    Neuronpedia

    INDEX
    Explanations

    Wars and foreign text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Định
    -0.07
     Tops
    -0.06
    rac
    -0.06
    创建
    -0.06
     Four
    -0.06
     شمال
    -0.06
    .integration
    -0.06
     intricate
    -0.06
    B
    -0.06
     Around
    -0.06
    POSITIVE LOGITS
     desn
    0.07
    -url
    0.07
    공부
    0.06
     declined
    0.06
    ificates
    0.06
     göster
    0.06
     culinary
    0.06
    .setCancelable
    0.06
     히
    0.06
    _good
    0.06
    Act Density 0.002%

    No Known Activations