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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thưởng
    -0.07
     colder
    -0.06
    ตรวจ
    -0.06
     shoes
    -0.06
    Posts
    -0.06
     newest
    -0.06
     liberty
    -0.06
     bones
    -0.06
     seldom
    -0.06
     router
    -0.06
    POSITIVE LOGITS
     Carm
    0.07
    ()]↵↵
    0.06
    ("").
    0.06
     徒歩
    0.06
    /QĐ
    0.06
     Packaging
    0.06
     bard
    0.06
    /^
    0.06
     Dış
    0.06
     alert
    0.06
    Act Density 0.041%

    No Known Activations