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

    Neuronpedia

    INDEX
    Explanations

    benchmarks and performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pause
    -0.07
     لح
    -0.07
     marginTop
    -0.07
     Edwin
    -0.06
     Agents
    -0.06
    .ne
    -0.06
     ridic
    -0.06
    .INPUT
    -0.06
    indow
    -0.06
    间
    -0.06
    POSITIVE LOGITS
     тва
    0.07
    告诉
    0.07
    -person
    0.06
     expressly
    0.06
    _Pos
    0.06
     dataSize
    0.06
    mysql
    0.06
     shark
    0.06
     سنگ
    0.06
     Vì
    0.06
    Act Density 0.027%

    No Known Activations