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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lộ
    -0.07
     sensitivity
    -0.07
    oods
    -0.07
     Rent
    -0.06
    ENCES
    -0.06
     Scot
    -0.06
    Hdr
    -0.06
     Comprehensive
    -0.06
     ACA
    -0.06
     انجمن
    -0.06
    POSITIVE LOGITS
    挥
    0.07
    灰
    0.07
     noexcept
    0.07
    adores
    0.07
    ViewController
    0.06
     mocked
    0.06
    isRequired
    0.06
     ulož
    0.06
    .aggregate
    0.06
     kvinder
    0.06
    Act Density 0.202%

    No Known Activations