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

    Neuronpedia

    INDEX
    Explanations

    benchmark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CRE
    -0.07
     रक
    -0.07
    戏
    -0.06
    -0.06
     外
    -0.06
    唇
    -0.06
    führt
    -0.06
     libros
    -0.06
    OTOS
    -0.06
    'S
    -0.06
    POSITIVE LOGITS
     benchmark
    0.15
     Benchmark
    0.12
     benchmarks
    0.11
    benchmark
    0.10
    Benchmark
    0.08
    enchmark
    0.08
    .fromRGBO
    0.07
    Holder
    0.07
    mt
    0.07
    داد
    0.07
    Act Density 0.002%

    No Known Activations