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

    Neuronpedia

    INDEX
    Explanations

    las

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𐤔
    -0.07
    chool
    -0.07
    纪检监察
    -0.07
    sku
    -0.06
    长城
    -0.06
     ויש
    -0.06
    𝕱
    -0.06
     międzyn
    -0.06
    홈
    -0.06
     TextFormField
    -0.06
    POSITIVE LOGITS
    寫
    0.07
     delta
    0.07
    -beta
    0.07
    Means
    0.07
    击
    0.07
     devour
    0.07
    اث
    0.07
     releases
    0.06
    вл
    0.06
    丹
    0.06
    Act Density 0.024%

    No Known Activations