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

    Neuronpedia

    INDEX
    Explanations

    legal cases remanded

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     directive
    -0.07
     lattice
    -0.07
     horizon
    -0.07
    цит
    -0.07
     elusive
    -0.07
     мероприятия
    -0.07
    lef
    -0.07
    pq
    -0.07
    ho
    -0.07
     niveau
    -0.06
    POSITIVE LOGITS
     Away
    0.07
    .StylePriority
    0.07
    뉜
    0.07
    ↵↵    ↵
    0.07
     dünyanın
    0.07
    ꀰ
    0.06
    明顯
    0.06
    ;\↵
    0.06
    펭
    0.06
    昏迷
    0.06
    Act Density 0.115%

    No Known Activations