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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    认识
    -0.08
    صرف
    -0.07
    categories
    -0.07
     답변
    -0.07
     thừa
    -0.07
    },{↵
    -0.06
    商品
    -0.06
     ensuite
    -0.06
    🏵
    -0.06
    Ϥ
    -0.06
    POSITIVE LOGITS
    .Charting
    0.08
    Lemma
    0.07
    とか
    0.07
     OG
    0.07
    /H
    0.07
     enrollment
    0.07
     fp
    0.07
     sağlık
    0.07
    bk
    0.07
     prise
    0.06
    Act Density 0.003%

    No Known Activations