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

    Neuronpedia

    INDEX
    Explanations

    # or //

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :The
    -0.07
    鼓励
    -0.07
    透气
    -0.07
    刑事案件
    -0.06
    话剧
    -0.06
     boils
    -0.06
    =E
    -0.06
    MING
    -0.06
    流浪
    -0.06
    羽毛球
    -0.06
    POSITIVE LOGITS
    /update
    0.08
    쵥
    0.08
    ToUpdate
    0.07
    สวน
    0.07
    谇
    0.07
     uploads
    0.07
    Senate
    0.07
     inadvertently
    0.07
    融创
    0.07
     opener
    0.07
    Act Density 0.002%

    No Known Activations