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

    Neuronpedia

    INDEX
    Explanations

    code URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    coach
    -0.06
     currentNode
    -0.06
     české
    -0.06
     несколько
    -0.06
     분류
    -0.06
     leží
    -0.06
     Bose
    -0.06
     prisons
    -0.06
     Week
    -0.06
     BST
    -0.06
    POSITIVE LOGITS
     müda
    0.08
    bove
    0.07
    الس
    0.07
     видно
    0.06
     اقتصادی
    0.06
    ージ
    0.06
    ้ด
    0.06
    ulously
    0.06
    ,uint
    0.06
     структур
    0.06
    Act Density 0.013%

    No Known Activations