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

    Neuronpedia

    INDEX
    Explanations

    Code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    崮
    -0.08
     oracle
    -0.07
     st
    -0.07
    蔺
    -0.07
    ✑
    -0.07
    转型发展
    -0.07
     jesteśmy
    -0.07
    ISOString
    -0.06
    頂き
    -0.06
    ߦ
    -0.06
    POSITIVE LOGITS
    asurer
    0.07
    ACY
    0.07
    .Right
    0.07
    퓨
    0.06
    .from
    0.06
    oric
    0.06
     Julian
    0.06
    ง
    0.06
    دل
    0.06
     judicial
    0.06
    Act Density 0.001%

    No Known Activations