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

    Neuronpedia

    INDEX
    Explanations

    code and languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Likewise
    -0.07
     NOTE
    -0.07
     Offer
    -0.07
     Winner
    -0.07
     Higher
    -0.07
     certainly
    -0.07
     longitude
    -0.07
     示例
    -0.07
    锧
    -0.06
    Exclusive
    -0.06
    POSITIVE LOGITS
    مباد
    0.08
    פסטיבל
    0.08
    经开
    0.07
    ทรา
    0.07
    markets
    0.07
    .people
    0.07
    טרה
    0.07
    👗
    0.07
    (','
    0.07
     kingdoms
    0.07
    Act Density 0.827%

    No Known Activations