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

    Neuronpedia

    INDEX
    Explanations

    descriptions and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     промислов
    -0.06
     Myers
    -0.06
    雨
    -0.06
    欢
    -0.06
    竟
    -0.06
    (Utils
    -0.06
    Ix
    -0.06
    何か
    -0.06
    兽
    -0.06
     Dexter
    -0.06
    POSITIVE LOGITS
    生成
    0.06
     Crafting
    0.06
     troubling
    0.06
     RED
    0.06
    Originally
    0.06
     fusion
    0.06
     christ
    0.06
     ram
    0.06
     rad
    0.06
     Rafael
    0.06
    Act Density 0.156%

    No Known Activations