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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Map
    -0.07
     emploi
    -0.07
    Approx
    -0.07
    也被
    -0.07
    Ṯ
    -0.07
    Ű
    -0.07
     Joh
    -0.06
    白沙
    -0.06
    Logs
    -0.06
    所需的
    -0.06
    POSITIVE LOGITS
    (`<
    0.08
     NEXT
    0.08
     serve
    0.07
    謇
    0.07
     SHALL
    0.07
    Tickets
    0.06
     设
    0.06
    aging
    0.06
    빈
    0.06
     Jaime
    0.06
    Act Density 0.041%

    No Known Activations