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

    Neuronpedia

    INDEX
    Explanations

    mediated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Funktion
    -0.07
     hike
    -0.07
     каждой
    -0.07
    獠
    -0.07
     struggles
    -0.07
    党的建设
    -0.07
     dönem
    -0.07
    •
    -0.06
    дрес
    -0.06
    بغ
    -0.06
    POSITIVE LOGITS
    .FirstOrDefault
    0.08
    osome
    0.07
    めて
    0.07
     intimate
    0.07
    (email
    0.07
    ados
    0.07
     impart
    0.07
    icial
    0.07
    אדם
    0.07
    匙
    0.07
    Act Density 0.009%

    No Known Activations