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

    Neuronpedia

    INDEX
    Explanations

    number sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cloud
    -0.07
    لق
    -0.07
    agma
    -0.07
     Fort
    -0.07
    ケ
    -0.07
     Ferm
    -0.07
    谢
    -0.07
     Mission
    -0.07
     Lease
    -0.07
    ὴ
    -0.07
    POSITIVE LOGITS
     >>>
    0.07
    漂亮
    0.07
     sider
    0.07
    岸边
    0.07
     النو
    0.06
     subdiv
    0.06
     Decide
    0.06
    研究报告
    0.06
    胍
    0.06
    打进
    0.06
    Act Density 0.003%

    No Known Activations