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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acağı
    -0.07
    𝚎
    -0.07
     llegó
    -0.07
     Marks
    -0.07
    触及
    -0.06
    instein
    -0.06
    𝚊
    -0.06
    舛
    -0.06
    ≠
    -0.06
    .card
    -0.06
    POSITIVE LOGITS
    寝
    0.08
    (getClass
    0.07
    搅
    0.07
    总面积
    0.07
    フリー
    0.07
    /moment
    0.06
    .getById
    0.06
     Mats
    0.06
    營
    0.06
    阈
    0.06
    Act Density 0.004%

    No Known Activations