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

    Neuronpedia

    INDEX
    Explanations

    Javascript libraries / code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    孩童
    -0.07
    דיווח
    -0.07
    底部
    -0.07
    credentials
    -0.07
    ities
    -0.07
    情景
    -0.07
    相较
    -0.06
    罅
    -0.06
     surrounding
    -0.06
    ively
    -0.06
    POSITIVE LOGITS
     bom
    0.07
     Zag
    0.07
    Goal
    0.07
    Exc
    0.07
    已完成
    0.07
    娛樂
    0.07
     Sho
    0.07
    唛
    0.06
    hid
    0.06
     Category
    0.06
    Act Density 0.001%

    No Known Activations