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

    Neuronpedia

    INDEX
    Explanations

    Biodiversity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deco
    -0.07
    Execution
    -0.07
     scram
    -0.06
     meilleure
    -0.06
    inyin
    -0.06
     symbol
    -0.06
    印
    -0.06
    Pow
    -0.06
    ительным
    -0.06
     Moreno
    -0.06
    POSITIVE LOGITS
     نیز
    0.07
    찮
    0.07
     EXT
    0.07
    .Al
    0.06
    협
    0.06
    .ng
    0.06
    /is
    0.06
    ・━・━・━・━
    0.06
    rece
    0.06
    _ft
    0.06
    Act Density 0.042%

    No Known Activations