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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蒡
    -0.07
    iciary
    -0.07
    冱
    -0.07
    책
    -0.06
    עלות
    -0.06
     PdfP
    -0.06
    连连
    -0.06
    :date
    -0.06
    淇
    -0.06
     hư
    -0.06
    POSITIVE LOGITS
    的核心
    0.08
    を選ぶ
    0.08
     Ctrl
    0.08
    AdminController
    0.08
    🕶
    0.07
     universally
    0.07
    (W
    0.07
     tips
    0.07
    ⺫
    0.07
    صاد
    0.07
    Act Density 0.474%

    No Known Activations